Working Directory
Importation du tableau de données
Téléchargement du tableau, garder surtout les informations des ordres
Sélection est faite à la main, pour chaque ordre (Diptera, Hymenoptera, Coleoptera) et pour la sélection Autres, correspond donc à tous les autres groupes n’appartenant pas à ces ordres.
En suite, on regroupe Arachnida étant donné qu’ils ne font pas partie des insectes.
Hymenoptera
Piege Hymeno
Extraction du tableau Filet & enlèvement des Soirs
Regroupement par individu dans le tableau Filet (division par 3 du nombre de lignes attendu)
Regroupement par individu dans le tableau Piège (passage de 81 à 27 lignes attendu)
filetH piegeH
Diptera
Piege Diptera
Extraction du tableau Filet & enlèvement des Soirs
Regroupement par individu dans le tableau Filet (division par 3 du nombre de lignes attendu)
Regroupement par individu dans le tableau Piège (passage de 81 à 27 lignes attendu)
filetD piegeD
Coleoptera
Piege Coleoptera
Extraction du tableau Filet & enlèvement des Soirs
Regroupement par individu dans le tableau Filet (division par 3 du nombre de lignes attendu)
Regroupement par individu dans le tableau Piège (passage de 81 à 27 lignes attendu)
filetC piegeC
Autres groupes d’insectes
Piege Autres
Extraction du tableau Filet & enlèvement des Soirs
Regroupement par individu dans le tableau Filet (division par 3 du nombre de lignes attendu)
Regroupement par individu dans le tableau Piège (passage de 81 à 27 lignes attendu)
###Récupération des matrices
Récupérer la matrice piege
Récupérer la matrice filet
Filet tout
filetfe<-subset(filet,filet$Saison=="Fevrier")
filetao<-subset(filet,filet$Saison=="Aout")
filetju<-subset(filet,filet$Saison=="Juin")
filetfex<-aggregate( . ~ identifiant_arbre, filetfe[,-(2:5)], sum)
filetfen<-aggregate( . ~ identifiant_arbre, filetfe[,(1:5)], max)
filetfe<-left_join(filetfen,filetfex,by="identifiant_arbre")
filetaox<-aggregate( . ~ identifiant_arbre, filetao[,-(2:5)], sum)
filetaon<-aggregate( . ~ identifiant_arbre, filetao[,(1:5)], max)
filetao<-left_join(filetaon,filetaox,by="identifiant_arbre")
filetjux<-aggregate( . ~ identifiant_arbre, filetju[,-(2:5)], sum)
filetjun<-aggregate( . ~ identifiant_arbre, filetju[,(1:5)], max)
filetju<-left_join(filetjun,filetjux,by="identifiant_arbre")
filetall<-bind_rows(filetju,filetao)
filetall<-bind_rows(filetall,filetfe)
Piege tout
piegefe<-subset(piege,piege$Saison=="Fevrier")
piegeao<-subset(piege,piege$Saison=="Aout")
piegeju<-subset(piege,piege$Saison=="Juin")
piegefex<-aggregate( . ~ identifiant_arbre, piegefe[,-(2:5)], sum)
piegefen<-aggregate( . ~ identifiant_arbre,piegefe[,(1:5)], max)
piegefe<-left_join(piegefen,piegefex,by="identifiant_arbre")
piegeaox<-aggregate( . ~ identifiant_arbre, piegeao[,-(2:5)], sum)
piegeaon<-aggregate( . ~ identifiant_arbre, piegeao[,(1:5)], max)
piegeao<-left_join(piegeaon,piegeaox,by="identifiant_arbre")
piegejux<-aggregate( . ~ identifiant_arbre, piegeju[,-(2:5)], sum)
piegejun<-aggregate( . ~ identifiant_arbre, piegeju[,(1:5)], max)
piegeju<-left_join(piegejun,piegejux,by="identifiant_arbre")
piegeall<-bind_rows(piegeju,piegeao)
piegeall<-bind_rows(piegeall,piegefe)
+Rang/Abondance Problème avec les courbes de raréfaction Calculs estimateurs des taux de complétude pour modèle réfaction (non utilisés ici mais pour avoir une base non biaisé si usage, à reprendre, ici la couverture)
Filet - Préparation du tableau
Piège - Préparation des tableaux
Filet - Modèle et Courbes
Pièges - Modèle et Courbes
#Estimateurs de diversité Filet selon la saison
ChaoRichness(NEX2)
## Observed Estimator Est_s.e. 95% Lower 95% Upper
## Aout 124 240.376 39.182 185.226 345.202
## Fevrier 159 305.759 45.495 240.052 424.735
## Juin 72 110.144 19.264 86.987 169.081
ChaoShannon(NEX2)
## Observed Estimator Est_s.e 95% Lower 95% Upper
## Aout 4.112 4.426 0.090 4.251 4.602
## Fevrier 4.104 4.364 0.082 4.204 4.523
## Juin 3.192 3.322 0.081 3.192 3.481
DataInfo(NEX2)
## Assemblage n S.obs SC f1 f2 f3 f4 f5 f6 f7 f8 f9 f10
## 1 Aout 401 124 0.8257 70 21 8 7 5 1 1 1 1 1
## 2 Fevrier 611 159 0.8626 84 24 15 8 8 2 3 1 1 1
## 3 Juin 458 72 0.9368 29 11 8 3 6 3 3 0 1 0
ChaoRichness(NEX2p)
## Observed Estimator Est_s.e. 95% Lower 95% Upper
## Aout 104 170.580 25.975 135.838 243.233
## Fevrier 90 257.878 70.213 166.425 458.767
## Juin 64 124.403 30.134 87.976 216.174
ChaoShannon(NEX2p)
## Observed Estimator Est_s.e 95% Lower 95% Upper
## Aout 3.491 3.649 0.076 3.499 3.799
## Fevrier 2.573 2.794 0.111 2.576 3.012
## Juin 2.661 2.763 0.063 2.661 2.887
DataInfo(NEX2p)
## Assemblage n S.obs SC f1 f2 f3 f4 f5 f6 f7 f8 f9 f10
## 1 Aout 584 104 0.9162 49 18 7 7 5 3 3 1 0 2
## 2 Fevrier 523 90 0.8892 58 10 5 3 2 3 2 1 0 0
## 3 Juin 624 64 0.9472 33 9 2 4 3 1 1 0 0 2
Tout
Distribution en log-norm? Seule qui fit
Si l’abondance de chaque espèce est proportionnelle aux ressources dont elle dispose, ->Ce mécanisme décrit assez bien un mécanisme de partage successif des ressources, par exemple entre groupes d’espèces de plus en plus petits, correspondant à des niches écologiques de plus en plus étroites
Phénomène d’emboîtement dans la méta-communauté ?
###Beta de Jaccard Diagramme de Venn - Filet
## (polygon[GRID.polygon.256], polygon[GRID.polygon.257], polygon[GRID.polygon.258], polygon[GRID.polygon.259], polygon[GRID.polygon.260], polygon[GRID.polygon.261], text[GRID.text.262], text[GRID.text.263], text[GRID.text.264], text[GRID.text.265], text[GRID.text.266], text[GRID.text.267], text[GRID.text.268], text[GRID.text.269], text[GRID.text.270], text[GRID.text.271])
Diagramme de Venn - Piege
## (polygon[GRID.polygon.272], polygon[GRID.polygon.273], polygon[GRID.polygon.274], polygon[GRID.polygon.275], polygon[GRID.polygon.276], polygon[GRID.polygon.277], text[GRID.text.278], text[GRID.text.279], text[GRID.text.280], text[GRID.text.281], text[GRID.text.282], text[GRID.text.283], text[GRID.text.284], text[GRID.text.285], text[GRID.text.286], text[GRID.text.287])
Préparation des données pour les calculs, conservation uniquement des “numeric”
Le nombre d’individus pour chaque espèce selon piège/filet
L’abondance d’insectes par arbre selon piège/filet
filet$norga<-apply(filetx,1,sum)
filet$norga
## [1] 7 0 2 6 11 5 4 3 3 2 1 2 2 4 2 1 2 0 1 2 0 2 2 3 3
## [26] 4 0 1 4 2 2 3 2 5 2 0 6 7 7 4 5 1 3 5 3 9 11 6 5 6
## [51] 14 17 10 16 16 4 8 6 46 27 29 24 17 28 19 30 30 51 36 6 32 20 9 11 11
## [76] 12 23 27 17 14 20 24 42 21 4 8 5 2 14 17 7 3 5 2 7 4 5 11 6 11
## [101] 4 31 18 26 19 3 30 11 3 3 4 2 29 4 2 0 2 2 2 2 1 3 2 5 6
## [126] 3 0 4 1 1 4 18 4 4 1 8 1 31 4 7 2 11 9 3 3 2 2 1 2 2
## [151] 3 2 9 2 1 1 2 0 0 2 3 74 2 7 4 0 6 3 0 1 1 4
piege$norga<-apply(piegex,1,sum)
piege$norga
## [1] 7 0 3 7 2 2 2 0 2 0 1 0 0 4 1 4 2 2
## [19] 9 1 1 2 0 1 1 9 1 4 25 4 41 7 1 5 5 6
## [37] 0 8 3 225 9 31 7 5 5 137 8 5 24 12 70 126 29 5
## [55] 13 24 80 49 134 20 7 21 7 3 3 22 6 46 3 23 8 6
## [73] 12 2 6 9 3 4 22 21 4 19 25 18 3 15 6 7 6 2
## [91] 2 1 6 8 41 7 16 9 11 1 2 16 34 17 15 5 4 6
l<-function(x){
x<-length(x[x!=0])
}
filet$rspe<-apply(filetx,1,l)
filet$rspe
## [1] 2 0 2 5 3 3 3 1 3 1 1 2 2 3 1 1 2 0 1 1 0 2 2 3 2
## [26] 2 0 1 2 2 1 3 2 2 2 0 5 3 4 4 2 1 2 5 2 6 8 3 4 6
## [51] 6 10 6 10 12 4 6 4 25 13 16 15 8 14 13 23 18 21 23 6 23 5 3 7 7
## [76] 7 9 8 8 4 7 5 9 5 4 5 4 2 7 8 4 2 3 2 6 4 4 7 5 7
## [101] 3 6 8 5 4 2 5 4 2 3 4 2 8 2 2 0 1 2 2 1 1 2 1 4 5
## [126] 1 0 3 1 1 3 7 3 3 1 5 1 10 3 3 2 4 3 3 3 1 2 1 2 2
## [151] 2 2 3 2 1 1 2 0 0 2 3 4 1 5 4 0 5 2 0 1 1 4
piege$rspe<-apply(piegex,1,l)
piege$rspe
## [1] 3 0 2 4 2 2 2 0 2 0 1 0 0 4 1 3 1 2 4 1 1 1 0 1 1
## [26] 3 1 3 15 4 8 7 1 4 3 5 0 4 3 1 7 2 6 5 5 6 2 3 8 7
## [51] 5 7 8 5 7 14 10 9 14 11 5 10 5 3 3 12 6 6 2 9 7 6 2 2 4
## [76] 3 2 4 4 5 4 2 6 4 2 5 5 4 5 2 2 1 4 6 12 4 7 5 8 1
## [101] 1 1 3 3 3 3 3 2
Tableau de synthèse (export en csv mieux)
###Analyses statstiques Partie 2 spécifique et d’abondance selon les méthodes des pièges et des filets pour chaque saison et l’effet saison / site
Filet - Richesse spécifique
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
glma<-glmer(rspe ~ site*Saison+(1|ordre), data = syntfilet, family=poisson, nAGQ=2) #Estimation des paramètres du modèle par la Quadrature de Gauss-Hermite (Bolker, 2008)
summary(glma)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * Saison + (1 | ordre)
## Data: syntfilet
##
## AIC BIC logLik deviance df.resid
## 286.3 317.7 -133.1 266.3 162
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.3412 -1.0107 -0.1219 0.7666 4.8066
##
## Random effects:
## Groups Name Variance Std.Dev.
## ordre (Intercept) 0.3535 0.5945
## Number of obs: 172, groups: ordre, 4
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.240e+00 3.175e-01 3.906 9.39e-05 ***
## siteExt_Reserve -4.041e-06 1.543e-01 0.000 0.999979
## siteReserve -1.001e-01 1.583e-01 -0.632 0.527240
## SaisonFevrier 5.179e-01 1.378e-01 3.758 0.000171 ***
## SaisonJuin -6.242e-01 1.847e-01 -3.379 0.000728 ***
## siteExt_Reserve:SaisonFevrier -3.949e-01 2.201e-01 -1.794 0.072807 .
## siteReserve:SaisonFevrier -9.508e-02 2.019e-01 -0.471 0.637748
## siteExt_Reserve:SaisonJuin 4.838e-01 2.444e-01 1.980 0.047751 *
## siteReserve:SaisonJuin 5.129e-01 2.490e-01 2.060 0.039379 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv SsnFvr SasnJn sE_R:SF stR:SF sE_R:SJ
## sitExt_Rsrv -0.243
## siteReserve -0.237 0.487
## SaisonFevrr -0.272 0.560 0.546
## SaisonJuin -0.203 0.418 0.407 0.468
## stExt_Rs:SF 0.170 -0.701 -0.342 -0.626 -0.293
## stRsrv:SsnF 0.186 -0.382 -0.784 -0.683 -0.319 0.427
## stExt_Rs:SJ 0.153 -0.631 -0.308 -0.353 -0.756 0.443 0.241
## stRsrv:SsnJ 0.151 -0.310 -0.636 -0.347 -0.742 0.217 0.498 0.561
Anova(glma, type=3, method="chisq") #methode chis2 car glmer et type 3 car plan déséquilibré et présence d'une interaction
## Analysis of Deviance Table (Type III Wald chisquare tests)
##
## Response: rspe
## Chisq Df Pr(>Chisq)
## (Intercept) 15.2554 1 9.391e-05 ***
## site 0.5242 2 0.769440
## Saison 47.8746 2 4.019e-11 ***
## site:Saison 14.0343 4 0.007186 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Test des résidus
library(DHARMa)
## This is DHARMa 0.4.6. For overview type '?DHARMa'. For recent changes, type news(package = 'DHARMa')
plot(simulateResiduals(glma))
library(MuMIn) #Détermination du r2
## Registered S3 method overwritten by 'MuMIn':
## method from
## model.frame.lme contrast
r.squaredGLMM(glma) #R2m représente le r avec seulement les effets fixes, et r2c il y a les effets de groupes
## Warning: 'r.squaredGLMM' now calculates a revised statistic. See the help page.
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## R2m R2c
## delta 0.1433366 0.6575384
## lognormal 0.1485238 0.6813336
## trigamma 0.1373694 0.6301646
#trigamma la plus fiable
TEST - PAIRWISE
emta1 <- lsmeans(glma, ~ site, by="Saison")
pairs(emta1)
## Saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.000004 0.154 Inf 0.000 1.0000
## (Bas-fond) - Reserve 0.100089 0.158 Inf 0.632 0.8024
## Ext_Reserve - Reserve 0.100085 0.158 Inf 0.632 0.8024
##
## Saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.394878 0.157 Inf 2.516 0.0319
## (Bas-fond) - Reserve 0.195167 0.125 Inf 1.557 0.2645
## Ext_Reserve - Reserve -0.199711 0.162 Inf -1.235 0.4327
##
## Saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.483801 0.190 Inf -2.553 0.0288
## (Bas-fond) - Reserve -0.412860 0.192 Inf -2.148 0.0803
## Ext_Reserve - Reserve 0.070941 0.169 Inf 0.421 0.9070
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emta2 <- lsmeans(glma, ~ Saison)
## NOTE: Results may be misleading due to involvement in interactions
pairs(emta2)
## contrast estimate SE df z.ratio p.value
## Aout - Fevrier -0.355 0.0883 Inf -4.015 0.0002
## Aout - Juin 0.292 0.0987 Inf 2.959 0.0087
## Fevrier - Juin 0.647 0.0965 Inf 6.697 <.0001
##
## Results are averaged over the levels of: site
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
Filet - Abondance
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
glmb<-glmer(norga ~ site*Saison+(1+Saison+site|ordre), data = syntfilet, family=poisson, nAGQ=1) #Estimation des paramètres du modèle par l'approximation de Laplace(Bolker, 2008) -> trop de facteurs aléatoires nécessaires au calcul du modèle pour faire une quadrature de Gausse-Hermite (impossible pour la fonction si plus de 1 et en général si + de 2,3)
## Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
## Model failed to converge with max|grad| = 0.00682423 (tol = 0.002, component 1)
summary(glmb)
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: poisson ( log )
## Formula: norga ~ site * Saison + (1 + Saison + site | ordre)
## Data: syntfilet
##
## AIC BIC logLik deviance df.resid
## 1289.5 1365.0 -620.7 1241.5 148
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6659 -1.1412 -0.4110 0.7298 15.9840
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## ordre (Intercept) 0.2463 0.4963
## SaisonFevrier 0.8893 0.9430 0.17
## SaisonJuin 0.5059 0.7113 0.83 -0.03
## siteExt_Reserve 0.5121 0.7156 -0.34 0.28 -0.81
## siteReserve 0.5170 0.7190 -0.79 0.45 -0.67 0.33
## Number of obs: 172, groups: ordre, 4
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.8807 0.2633 7.142 9.17e-13 ***
## siteExt_Reserve -0.1872 0.3814 -0.491 0.62352
## siteReserve -0.1718 0.3822 -0.450 0.65301
## SaisonFevrier -0.1325 0.4888 -0.271 0.78632
## SaisonJuin -1.0376 0.3863 -2.686 0.00724 **
## siteExt_Reserve:SaisonFevrier 0.1624 0.1762 0.922 0.35667
## siteReserve:SaisonFevrier 0.2428 0.1654 1.467 0.14224
## siteExt_Reserve:SaisonJuin 1.3038 0.1857 7.020 2.22e-12 ***
## siteReserve:SaisonJuin 1.1610 0.1888 6.151 7.71e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv SsnFvr SasnJn sE_R:SF stR:SF sE_R:SJ
## sitExt_Rsrv -0.378
## siteReserve -0.776 0.348
## SaisonFevrr 0.100 0.288 0.446
## SaisonJuin 0.655 -0.651 -0.539 0.019
## stExt_Rs:SF 0.150 -0.219 -0.103 -0.156 -0.116
## stRsrv:SsnF 0.163 -0.109 -0.236 -0.167 -0.128 0.480
## stExt_Rs:SJ 0.134 -0.211 -0.091 -0.083 -0.290 0.495 0.254
## stRsrv:SsnJ 0.137 -0.089 -0.212 -0.085 -0.287 0.235 0.541 0.563
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## Model failed to converge with max|grad| = 0.00682423 (tol = 0.002, component 1)
Anova(glmb, type=3, method="chisq") #methode chis2 car glmer et type 3 car plan déséuilibré
## Analysis of Deviance Table (Type III Wald chisquare tests)
##
## Response: norga
## Chisq Df Pr(>Chisq)
## (Intercept) 51.0137 1 9.173e-13 ***
## site 0.3294 2 0.84816
## Saison 7.2623 2 0.02649 *
## site:Saison 64.3497 4 3.527e-13 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Test des résidus
library(DHARMa)
plot(simulateResiduals(glmb))
library(MuMIn) #Détermination du r2
r.squaredGLMM(glmb) #R2m représente le r avec seulement les effets fixes, et r2c il y a les effets de groupes
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## boundary (singular) fit: see help('isSingular')
## R2m R2c
## delta 0.08901978 0.9067331
## lognormal 0.08943409 0.9109532
## trigamma 0.08856513 0.9021022
#trigamma la plus fiable
PAIRWISE
emtb1 <- lsmeans(glmb, ~ site, by="Saison")
pairs(emtb1)
## Saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.1872 0.381 Inf 0.491 0.8757
## (Bas-fond) - Reserve 0.1718 0.382 Inf 0.450 0.8946
## Ext_Reserve - Reserve -0.0154 0.436 Inf -0.035 0.9993
##
## Saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.0249 0.383 Inf 0.065 0.9977
## (Bas-fond) - Reserve -0.0709 0.379 Inf -0.187 0.9809
## Ext_Reserve - Reserve -0.0958 0.435 Inf -0.220 0.9736
##
## Saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -1.1166 0.387 Inf -2.882 0.0110
## (Bas-fond) - Reserve -0.9892 0.389 Inf -2.545 0.0294
## Ext_Reserve - Reserve 0.1274 0.431 Inf 0.295 0.9530
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emtb2 <- lsmeans(glmb, ~ Saison) #changer l'écriture de la formule
## NOTE: Results may be misleading due to involvement in interactions
pairs(emtb2)
## contrast estimate SE df z.ratio p.value
## Aout - Fevrier -0.00254 0.480 Inf -0.005 1.0000
## Aout - Juin 0.21600 0.366 Inf 0.591 0.8250
## Fevrier - Juin 0.21854 0.606 Inf 0.361 0.9308
##
## Results are averaged over the levels of: site
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
Piege - Richesse spécifique
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.4), : Ignoring unknown aesthetics: ymin and ymax
glmc<-glmer(rspe ~ site*Saison+(1|ordre), data = syntpiege, family=poisson, nAGQ=2)
summary(glmc)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * Saison + (1 | ordre)
## Data: syntpiege
##
## AIC BIC logLik deviance df.resid
## 182.4 209.2 -81.2 162.4 98
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.2761 -0.7517 -0.1570 0.4861 4.3142
##
## Random effects:
## Groups Name Variance Std.Dev.
## ordre (Intercept) 0.258 0.5079
## Number of obs: 108, groups: ordre, 4
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.3361 0.2911 4.589 4.45e-06 ***
## siteExt_Reserve 0.0290 0.1841 0.158 0.87483
## siteReserve 0.3309 0.1836 1.803 0.07146 .
## SaisonFevrier 0.2271 0.1877 1.210 0.22641
## SaisonJuin -0.6360 0.2380 -2.672 0.00754 **
## siteExt_Reserve:SaisonFevrier -0.1448 0.2754 -0.526 0.59893
## siteReserve:SaisonFevrier -0.7762 0.2715 -2.859 0.00425 **
## siteExt_Reserve:SaisonJuin 0.3640 0.3097 1.175 0.23984
## siteReserve:SaisonJuin 0.2235 0.3033 0.737 0.46131
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv SsnFvr SasnJn sE_R:SF stR:SF sE_R:SJ
## sitExt_Rsrv -0.366
## siteReserve -0.367 0.580
## SaisonFevrr -0.359 0.567 0.569
## SaisonJuin -0.283 0.447 0.449 0.439
## stExt_Rs:SF 0.245 -0.669 -0.388 -0.682 -0.299
## stRsrv:SsnF 0.248 -0.392 -0.676 -0.691 -0.303 0.471
## stExt_Rs:SJ 0.217 -0.594 -0.345 -0.337 -0.768 0.397 0.233
## stRsrv:SsnJ 0.222 -0.351 -0.605 -0.344 -0.785 0.235 0.409 0.603
Anova(glmc, type=3, method="chisq")
## Analysis of Deviance Table (Type III Wald chisquare tests)
##
## Response: rspe
## Chisq Df Pr(>Chisq)
## (Intercept) 21.061 1 4.448e-06 ***
## site 4.439 2 0.1086621
## Saison 14.172 2 0.0008369 ***
## site:Saison 13.562 4 0.0088326 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Test des résidus
library(DHARMa)
plot(simulateResiduals(glmc))
library(MuMIn) #Détermination du r2
r.squaredGLMM(glmc) #R2m représente le r avec seulement les effets fixes, et r2c il y a les effets de groupes
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## R2m R2c
## delta 0.1301930 0.5842498
## lognormal 0.1359748 0.6101962
## trigamma 0.1236490 0.5548831
#trigamma la plus fiable
TEST - PAIRWISE
emtc1 <- lsmeans(glmc, ~ site, by="Saison")
pairs(emtc1)
## Saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.029 0.184 Inf -0.158 0.9864
## (Bas-fond) - Reserve -0.331 0.184 Inf -1.803 0.1687
## Ext_Reserve - Reserve -0.302 0.168 Inf -1.792 0.1722
##
## Saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.116 0.205 Inf 0.566 0.8384
## (Bas-fond) - Reserve 0.445 0.200 Inf 2.226 0.0668
## Ext_Reserve - Reserve 0.329 0.225 Inf 1.463 0.3088
##
## Saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.393 0.249 Inf -1.578 0.2551
## (Bas-fond) - Reserve -0.554 0.241 Inf -2.295 0.0564
## Ext_Reserve - Reserve -0.161 0.215 Inf -0.750 0.7338
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emtc2 <- lsmeans(glmc, ~ Saison)
## NOTE: Results may be misleading due to involvement in interactions
pairs(emtc2)
## contrast estimate SE df z.ratio p.value
## Aout - Fevrier 0.0799 0.113 Inf 0.709 0.7580
## Aout - Juin 0.4402 0.121 Inf 3.644 0.0008
## Fevrier - Juin 0.3602 0.129 Inf 2.794 0.0144
##
## Results are averaged over the levels of: site
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
Piege - Abondance
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.4), : Ignoring unknown aesthetics: ymin and ymax
glmd<-glmer(norga ~ site*Saison+(1+site+Saison|ordre), data = syntpiege, family=poisson)
## Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
## Model failed to converge with max|grad| = 0.0101821 (tol = 0.002, component 1)
summary(glmd)
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: poisson ( log )
## Formula: norga ~ site * Saison + (1 + site + Saison | ordre)
## Data: syntpiege
##
## AIC BIC logLik deviance df.resid
## 1603.0 1667.4 -777.5 1555.0 84
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -7.8631 -1.5024 -0.4863 1.1697 19.1190
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## ordre (Intercept) 1.1881 1.0900
## siteExt_Reserve 0.2843 0.5332 -0.44
## siteReserve 1.0735 1.0361 -0.49 0.51
## SaisonFevrier 0.7956 0.8920 -0.71 0.94 0.68
## SaisonJuin 1.1089 1.0530 -0.88 0.82 0.60 0.95
## Number of obs: 108, groups: ordre, 4
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.3290 0.5629 2.361 0.01823 *
## siteExt_Reserve 0.4757 0.3152 1.509 0.13124
## siteReserve 1.5333 0.5407 2.836 0.00457 **
## SaisonFevrier 0.5525 0.4787 1.154 0.24844
## SaisonJuin 0.1153 0.5609 0.205 0.83720
## siteExt_Reserve:SaisonFevrier 0.0898 0.2048 0.439 0.66102
## siteReserve:SaisonFevrier -1.0473 0.1916 -5.465 4.62e-08 ***
## siteExt_Reserve:SaisonJuin 0.4479 0.2227 2.012 0.04426 *
## siteReserve:SaisonJuin -0.3416 0.2127 -1.606 0.10834
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv SsnFvr SasnJn sE_R:SF stR:SF sE_R:SJ
## sitExt_Rsrv -0.467
## siteReserve -0.514 0.519
## SaisonFevrr -0.706 0.841 0.670
## SaisonJuin -0.859 0.740 0.596 0.902
## stExt_Rs:SF 0.134 -0.361 -0.137 -0.258 -0.140
## stRsrv:SsnF 0.149 -0.252 -0.192 -0.285 -0.157 0.657
## stExt_Rs:SJ 0.133 -0.356 -0.137 -0.151 -0.273 0.553 0.365
## stRsrv:SsnJ 0.145 -0.245 -0.187 -0.165 -0.294 0.355 0.535 0.727
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## Model failed to converge with max|grad| = 0.0101821 (tol = 0.002, component 1)
Anova(glmd, type=3, method="chisq")
## Analysis of Deviance Table (Type III Wald chisquare tests)
##
## Response: norga
## Chisq Df Pr(>Chisq)
## (Intercept) 5.5742 1 0.01823 *
## site 8.0423 2 0.01793 *
## Saison 5.0907 2 0.07844 .
## site:Saison 63.0661 4 6.572e-13 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Test des résidus
library(DHARMa)
plot(simulateResiduals(glmd))
library(MuMIn) #Détermination du r2
r.squaredGLMM(glmd) #R2m représente le r avec seulement les effets fixes, et r2c il y a les effets de groupes
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## boundary (singular) fit: see help('isSingular')
## R2m R2c
## delta 0.1779598 0.9271632
## lognormal 0.1785965 0.9304803
## trigamma 0.1772606 0.9235204
#trigamma la plus fiable
TEST - PAIRWISE
emtd1 <- lsmeans(glmd, ~ site, by="Saison")
pairs(emtd1)
## Saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.4757 0.315 Inf -1.509 0.2865
## (Bas-fond) - Reserve -1.5333 0.541 Inf -2.836 0.0127
## Ext_Reserve - Reserve -1.0576 0.464 Inf -2.281 0.0584
##
## Saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.5655 0.308 Inf -1.838 0.1572
## (Bas-fond) - Reserve -0.4860 0.538 Inf -0.903 0.6381
## Ext_Reserve - Reserve 0.0795 0.465 Inf 0.171 0.9840
##
## Saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.9236 0.315 Inf -2.936 0.0093
## (Bas-fond) - Reserve -1.1917 0.543 Inf -2.195 0.0720
## Ext_Reserve - Reserve -0.2681 0.462 Inf -0.580 0.8308
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emtd2 <- lsmeans(glmd, ~ Saison)
## NOTE: Results may be misleading due to involvement in interactions
pairs(emtd2)
## contrast estimate SE df z.ratio p.value
## Aout - Fevrier -0.2333 0.458 Inf -0.510 0.8665
## Aout - Juin -0.1507 0.535 Inf -0.281 0.9573
## Fevrier - Juin 0.0826 0.195 Inf 0.424 0.9058
##
## Results are averaged over the levels of: site
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
Tester l’ajustement du modèle avec le plus faible AIC :
library(AICcmodavg)
##
## Attaching package: 'AICcmodavg'
## The following objects are masked from 'package:MuMIn':
##
## AICc, DIC, importance
## The following object is masked from 'package:lme4':
##
## checkConv
#aictab(list(glm1, glm1f))
Floraison en facteur aléatoire La relation entre rspe et site peut varier selon la saison par contre
TEST - PAIRWISE
library(emmeans)
emtd1 <- lsmeans(glmd, ~ site, by="Saison")
pairs(emta1)
## Saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.000004 0.154 Inf 0.000 1.0000
## (Bas-fond) - Reserve 0.100089 0.158 Inf 0.632 0.8024
## Ext_Reserve - Reserve 0.100085 0.158 Inf 0.632 0.8024
##
## Saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.394878 0.157 Inf 2.516 0.0319
## (Bas-fond) - Reserve 0.195167 0.125 Inf 1.557 0.2645
## Ext_Reserve - Reserve -0.199711 0.162 Inf -1.235 0.4327
##
## Saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.483801 0.190 Inf -2.553 0.0288
## (Bas-fond) - Reserve -0.412860 0.192 Inf -2.148 0.0803
## Ext_Reserve - Reserve 0.070941 0.169 Inf 0.421 0.9070
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emtd2 <- lsmeans(glmd, ~ Saison)
## NOTE: Results may be misleading due to involvement in interactions
pairs(emtd2)
## contrast estimate SE df z.ratio p.value
## Aout - Fevrier -0.2333 0.458 Inf -0.510 0.8665
## Aout - Juin -0.1507 0.535 Inf -0.281 0.9573
## Fevrier - Juin 0.0826 0.195 Inf 0.424 0.9058
##
## Results are averaged over the levels of: site
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
###Analyses multivariées PCoA /Ok On veut montrer la différence de communauté entre saisons pour les Insectes en général, cf ensuite pour faire selon Ordre -> et voir si on fait aussi des PCo pour l’effet site ou on se contente de la Permanova
https://rpubs.com/hafezahmad/948799 ################################################################################
#Partie 1 : Saison Création des matrices Méthode Bray-Curtis -> vegdist + correction de hellinger -> wcmdscale, add lingoes ->adonis2, 5000 permutations
Filet
Piege
Tout
colmet<-c("#CDDC39","#000000")
ordiplot(pcoamet,display="sites",type="n")
points (pcoa, col = colmet[all$method], pch=18, cex=2)
legend("bottomright", legend=levels(all$method), pt.bg=colmet, pt.cex=1.2, y.intersp=.7,x.intersp=.7, pch = 21, cex=1)
title("PCoA.Method")
PCoA.Filet-Saison
PCoA.Piege-Saison
Permanova.Filet - Saison - Site
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_filet[, 6:406] ~ as.factor(m_filet$Saison) * as.factor(m_filet$site), data = m_filet, permutations = 5000)
## Df SumOfSqs R2 F
## as.factor(m_filet$Saison) 2 4.6062 0.26610 8.5177
## as.factor(m_filet$site) 2 1.1923 0.06888 2.2047
## as.factor(m_filet$Saison):as.factor(m_filet$site) 4 2.3183 0.13393 2.1435
## Residual 34 9.1933 0.53110
## Total 42 17.3100 1.00000
## Pr(>F)
## as.factor(m_filet$Saison) 0.0002000 ***
## as.factor(m_filet$site) 0.0003999 ***
## as.factor(m_filet$Saison):as.factor(m_filet$site) 0.0002000 ***
## Residual
## Total
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
pairwise.adonis <- function(resp,fact,p.method="fdr") {
if (nrow(resp)!=length(fact)) {
stop(paste("'",deparse(substitute(resp)),"' and '",deparse(substitute(fact)),
"lengths differ",sep=""))
}
if (!is.factor(fact)) {fact <- factor(fact)}
data.name <- paste(deparse(substitute(resp))," and ",deparse(substitute(fact)),sep="")
fun.p <- function(i,j) {
resp2 <- resp[as.numeric(fact)%in%c(i,j),]
fact2 <- droplevels(fact[as.numeric(fact)%in%c(i,j)])
adonis(resp2~fact2)$aov.tab[1,"Pr(>F)"]
}
multcomp <- pairwise.table(fun.p,levels(fact),p.adjust.method=p.method)
result <- list(method="permutational MANOVAs",data.name=data.name,p.value=multcomp,p.adjust.method=p.method)
class(result) <- "pairwise.htest"
return(result)
}
Pairwise permanova - Filet
pairwise.adonis (resp = m_filet[,6:406], fact = as.factor(m_filet$Saison), p.method="fdr")
## 'adonis' will be deprecated: use 'adonis2' instead
## 'adonis' will be deprecated: use 'adonis2' instead
## 'adonis' will be deprecated: use 'adonis2' instead
##
## Pairwise comparisons using permutational MANOVAs
##
## data: m_filet[, 6:406] and as.factor(m_filet$Saison)
##
## Aout Fevrier
## Fevrier 0.001 -
## Juin 0.001 0.001
##
## P value adjustment method: fdr
Permanova.Piege - Saison
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Blocks: strata
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_piege[, 6:406] ~ as.factor(m_piege$Saison) * as.factor(m_piege$site), data = m_piege, permutations = 5000, strata = m_piege$site)
## Df SumOfSqs R2 F
## as.factor(m_piege$Saison) 2 2.4790 0.21318 3.8153
## as.factor(m_piege$site) 2 1.2346 0.10618 1.9002
## as.factor(m_piege$Saison):as.factor(m_piege$site) 4 2.0670 0.17776 1.5907
## Residual 18 5.8476 0.50288
## Total 26 11.6283 1.00000
## Pr(>F)
## as.factor(m_piege$Saison) 0.000200 ***
## as.factor(m_piege$site) 0.000200 ***
## as.factor(m_piege$Saison):as.factor(m_piege$site) 0.003599 **
## Residual
## Total
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Pairwise permanova - Piege
pairwise.adonis (resp = m_piege[,6:406], fact = as.factor(m_piege$Saison), p.method="fdr")
## 'adonis' will be deprecated: use 'adonis2' instead
## 'adonis' will be deprecated: use 'adonis2' instead
## 'adonis' will be deprecated: use 'adonis2' instead
##
## Pairwise comparisons using permutational MANOVAs
##
## data: m_piege[, 6:406] and as.factor(m_piege$Saison)
##
## Aout Fevrier
## Fevrier 0.001 -
## Juin 0.001 0.001
##
## P value adjustment method: fdr
#Partie 2 : Effet restauration
Création des matrices : PCoA Piege
Juin PCoA. Filet - Site // Piege - Site (vérifier si légendes sur les bons points)
Aout
Février
PERMANOVA. Filet - Aout
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_fileta[, 6:406] ~ as.factor(m_fileta$site), data = m_fileta, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_fileta$site) 2 1.2696 0.25586 2.063 2e-04 ***
## Residual 12 3.6927 0.74414
## Total 14 4.9623 1.00000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 'adonis' will be deprecated: use 'adonis2' instead
## 'adonis' will be deprecated: use 'adonis2' instead
## 'adonis' will be deprecated: use 'adonis2' instead
##
## Pairwise comparisons using permutational MANOVAs
##
## data: m_fileta[, 6:406] and as.factor(m_fileta$site)
##
## Bas-fond Ext_Reserve
## Ext_Reserve 0.077 -
## Reserve 0.013 0.013
##
## P value adjustment method: fdr
PERMANOVA - Piege - Aout
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_piegea[, 6:406] ~ as.factor(m_piegea$site), data = m_piegea, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_piegea$site) 2 1.2524 0.36009 1.9696 0.0018 **
## Residual 7 2.2256 0.63991
## Total 9 3.4780 1.00000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 'adonis' will be deprecated: use 'adonis2' instead
## Set of permutations < 'minperm'. Generating entire set.
## 'adonis' will be deprecated: use 'adonis2' instead
## 'nperm' >= set of all permutations: complete enumeration.
## Set of permutations < 'minperm'. Generating entire set.
## 'adonis' will be deprecated: use 'adonis2' instead
## Set of permutations < 'minperm'. Generating entire set.
##
## Pairwise comparisons using permutational MANOVAs
##
## data: m_piegea[, 6:406] and as.factor(m_piegea$site)
##
## Bas-fond Ext_Reserve
## Ext_Reserve 0.12 -
## Reserve 0.12 0.12
##
## P value adjustment method: fdr
PERMANOVA - Filet - Février
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_filetf[, 6:406] ~ as.factor(m_filetf$site), data = m_filetf, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_filetf$site) 2 1.4412 0.37264 2.9699 2e-04 ***
## Residual 10 2.4264 0.62736
## Total 12 3.8676 1.00000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 'adonis' will be deprecated: use 'adonis2' instead
## 'adonis' will be deprecated: use 'adonis2' instead
## 'adonis' will be deprecated: use 'adonis2' instead
##
## Pairwise comparisons using permutational MANOVAs
##
## data: m_filetf[, 6:406] and as.factor(m_filetf$site)
##
## Bas-fond Ext_Reserve
## Ext_Reserve 0.026 -
## Reserve 0.026 0.104
##
## P value adjustment method: fdr
*PERMANOVA - Piege - Février
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_piegef[, 6:406] ~ as.factor(m_piegef$site), data = m_piegef, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_piegef$site) 2 0.9014 0.32579 1.208 0.1218
## Residual 5 1.8654 0.67421
## Total 7 2.7668 1.00000
## 'adonis' will be deprecated: use 'adonis2' instead
## 'nperm' >= set of all permutations: complete enumeration.
## Set of permutations < 'minperm'. Generating entire set.
## 'adonis' will be deprecated: use 'adonis2' instead
## 'nperm' >= set of all permutations: complete enumeration.
## Set of permutations < 'minperm'. Generating entire set.
## 'adonis' will be deprecated: use 'adonis2' instead
## 'nperm' >= set of all permutations: complete enumeration.
## Set of permutations < 'minperm'. Generating entire set.
##
## Pairwise comparisons using permutational MANOVAs
##
## data: m_piegef[, 6:406] and as.factor(m_piegef$site)
##
## Bas-fond Ext_Reserve
## Ext_Reserve 0.15 -
## Reserve 0.15 0.90
##
## P value adjustment method: fdr
PERMANOVA - Filet - Juin
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_filetj[, 6:406] ~ as.factor(m_filetj$site), data = m_filetj, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_filetj$site) 2 0.7997 0.20643 1.5608 0.006599 **
## Residual 12 3.0742 0.79357
## Total 14 3.8739 1.00000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 'adonis' will be deprecated: use 'adonis2' instead
## 'adonis' will be deprecated: use 'adonis2' instead
## 'adonis' will be deprecated: use 'adonis2' instead
##
## Pairwise comparisons using permutational MANOVAs
##
## data: m_filetj[, 6:406] and as.factor(m_filetj$site)
##
## Bas-fond Ext_Reserve
## Ext_Reserve 0.117 -
## Reserve 0.009 0.050
##
## P value adjustment method: fdr
PERMANOVA - Piege - Juin
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_piegej[, 6:406] ~ as.factor(m_piegej$site), data = m_piegej, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_piegej$site) 2 1.1479 0.39521 1.9604 0.003799 **
## Residual 6 1.7566 0.60479
## Total 8 2.9044 1.00000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 'adonis' will be deprecated: use 'adonis2' instead
## 'nperm' >= set of all permutations: complete enumeration.
## Set of permutations < 'minperm'. Generating entire set.
## 'adonis' will be deprecated: use 'adonis2' instead
## 'nperm' >= set of all permutations: complete enumeration.
## Set of permutations < 'minperm'. Generating entire set.
## 'adonis' will be deprecated: use 'adonis2' instead
## 'nperm' >= set of all permutations: complete enumeration.
## Set of permutations < 'minperm'. Generating entire set.
##
## Pairwise comparisons using permutational MANOVAs
##
## data: m_piegej[, 6:406] and as.factor(m_piegej$site)
##
## Bas-fond Ext_Reserve
## Ext_Reserve 0.1 -
## Reserve 0.1 0.1
##
## P value adjustment method: fdr
Peu de différences sur les PCoA mais significatif en Permanova ? Regarder si bonnes représentations avec deux axes, demander Magali
#Tableau de diversité & Classification
test<-read.csv("test.csv",header = T, row.names = NULL,sep = ";")
test2<-read.csv("test2.csv",header = T, row.names = NULL,sep = ";")
library(dplyr)
test0<-inner_join(test,test2,by="morphotype")
Abondances des espèces
fipia<-fipi[,(1:406)]
fipix<-fipia[,6:406]
fipiabu<-apply(fipix,2,sum)
fipiabu<-data.frame(fipiabu)
fipiabu$morphotype<-rownames(fipiabu)
Fusion
test0<-left_join(test0,fipiabu,by="morphotype")
#Informations
ggplot(synt) +
aes(x = site, y = norga, fill = ordre) +
geom_col() +
scale_fill_manual(
values = c(Autres = "#FFFFF0",
Coleoptera = "#FF5722",
Diptera = "#CDDC39",
Hymenoptera = "#26A69A")
) +
theme_dark() +
facet_wrap(vars(Saison)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +ggtitle("Abondance-Tout") +
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
fipinew$rspe<-apply(fipinew[,3:403],1,l)
fipinew$rspe
## [1] 17 15 14 14 7 10 23 30 34 27 41 32 18 16 13 10 6 5 25 17 31 80 33 51 9
## [26] 14 10 4 5 11 9 11 15 21 29 29
ggplot(fipinew) +
aes(x = site, y = rspe, fill = ordre) +
geom_col() +
scale_fill_manual(
values = c(Autres = "#FFFFF0",
Coleoptera = "#FF5722",
Diptera = "#CDDC39",
Hymenoptera = "#26A69A")
) +
theme_dark() +
facet_wrap(vars(saison)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +ggtitle("Richesse spécifique-Tout") +
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
fipinewbis<-fipinew[,-(3:403)]
Au piège, rien d’intéressant mais au filet : halict 17, halict 1,2,3 sont présentes sur les trois saisons.
Chercher ces espèces avec data pièges
Espèces les plus abondantes
## formic.8 formic.1 halict.3 mythic.3
## 264 204 162 154
## rhinop.1 phlaeo.4 bracon.1 lepido.1
## 113 101 100 97
## phorid.2 cicade.5 halict.17 muscid.1
## 81 65 62 61
## formic.13 aphido.1 chloro.1 platyg.1
## 50 46 42 36
## aleyro.1 formic.4 bracon.4 chryso.3
## 35 34 31 27
## chloro.3 halict.2 phlaeo.1 bracon.13
## 27 26 25 23
## euloph.4 eupelm.2 mirida.6 formic.3
## 22 22 22 21
## meloid.2 phorid.4 chloro.5 bombyl.2
## 20 20 18 18
## chrysol.2 crabro.4 mythic.5 chloro.2
## 17 17 17 17
## chryso.4 platyg.2 cerato.6 phorid.3
## 16 16 16 16
## milich.5 tachin.1 coccin.1 eupelm.12
## 15 15 14 14
## cicade.3 phlaeo.6 crabro.13 bracon.7
## 14 14 13 13
## euloph.5 euryto.1 mirida.2 curcul.1
## 11 11 11 10
## chrysol.1 formic.14 formic.2 thynni.1
## 10 10 10 10
## chloro.4 cerato.1 meloid.1 chalci.2
## 10 10 9 9
## euloph.1 phlaeo.9 bupres.1 perila.1
## 9 9 8 8
## crabro.3 bombyl.6 chloro.6 mythic.4
## 8 8 8 8
## dermes.1 platyg.3 cecido.8 chloro.9
## 7 7 7 7
## chiron.1 dolich.2 mythic.7 muscid.6
## 7 7 7 7
## loncha.1 lepido.6 ptinid.1 mordel.1
## 7 7 6 6
## coccin.5 euloph.14 ormyri.2 euloph.7
## 6 6 6 6
## crabro.2 thynni.2 muscid.7 phorid.1
## 6 6 6 6
## chryso.5 bupres.2 platyg.4 euryto.3
## 5 5 5 5
## bracon.12 encyrt.4 euryto.2 tetrac.5
## 5 5 5 5
## eupelm.4 bracon.8 eupelm.3 bracon.5
## 5 5 5 5
## pterom.1(platyg) eupelm.1 formic.6 euloph.2
## 5 5 5 5
## halict.1 cecido.6 mythic.8 drosop.4
## 5 5 5 5
## muscid.3 sarcop.2 cicade.7 phlaeo.8
## 5 5 5 5
## coniop.1 lepido.4 hemipt.2 cicade.1
## 5 5 5 5
## staphy.3 dermes.3 meloid.3 coccin.3
## 4 4 4 4
## dermes.2 curcul.2 bracon.14 euloph.12
## 4 4 4 4
## eupelm.11 encyrt.3 crabro.14 pterom.10
## 4 4 4 4
## megasp.1 coccin.2 loncha.2 muscid.4
## 4 4 4 4
## cerato.7 crypto.1 muscid.5 muscid.2
## 4 4 4 4
## psocop.4 lepido.7 acrid.1 coniop.2
## 4 4 4 4
## coccin.6 dermes.4 coccin.4 liopte.1
## 3 3 3 3
## signip.1 formic.19 tetrac.7 euloph.13
## 3 3 3 3
## crabro.15 euloph.9 pterom.5 crabro.9
## 3 3 3 3
## mutill.2 apidae.6 euloph.3 scolii.2
## 3 3 3 3
## cecido.7 bombyl.5 apsilo.1 rhinii.2
## 3 3 3 3
## milich.4 asilid.1 cecido.1 mythic.1
## 3 3 3 3
## achili.1 phlaeo.5 lepido.3 tingid.1
## 3 3 3 3
## lepido.2 mirida.1 chryso.13 chryso.6
## 3 3 2 2
## chryso.12 carabi.4 coleop.2 pompil.5
## 2 2 2 2
## formic.20 halict.19 eupelm.14 bethyl.10
## 2 2 2 2
## thynni.5 halict.18 eupelm.13 pompil.3
## 2 2 2 2
## perila.4 crabro.17 apheli.2 pterom.4
## 2 2 2 2
## encyrt.9 encyrt.10 mymari.1 tricho.1
## 2 2 2 2
## encyrt.5 eupelm.10 hymeno.8 encyrt.2
## 2 2 2 2
## eupelm.8 crabro.10 bracon.11 apheli.1
## 2 2 2 2
## eupelm.5 apidae.5 tetrac.3 hymeno.3
## 2 2 2 2
## chalci.4 formic.15 formic.12 formic.11
## 2 2 2 2
## formic.9 apidae.1 ichneu.1 scolii.1
## 2 2 2 2
## chamae.1 chloro.11 chiron.3 tephri.4
## 2 2 2 2
## chloro.8 odinii.1 anthom.1 rhinii.3
## 2 2 2 2
## dipter.15 asilid.3 asilid.2 dipter.13
## 2 2 2 2
## cerato.3 drosop.1 rhaphi.1 anthoc.1
## 2 2 2 2
## lepido.5 neurop.2 cicade.4 cicade.2
## 2 2 2 2
## aleyro.2 hemipt.1 leiodi.1 coccin.7
## 2 2 1 1
## cerylo.1 nitidu.1 chryso.8 meloid.4
## 1 1 1 1
## staphy.2 chryso.2 elater.1 lycida.1
## 1 1 1 1
## crabro.21 formic.21 crabro.20 euloph.18
## 1 1 1 1
## pterom.9 tetrac.8 encyrt.16 ichneu.3
## 1 1 1 1
## crabro.18 pterom.8 bethyl.11 encyrt.15
## 1 1 1 1
## encyrt.14 andren.1 dryini.1 pterom.7
## 1 1 1 1
## ceraph.4 diapar.1 euloph.16 eutric.1
## 1 1 1 1
## pompil.4 betyhl.7 scolii.3 encyrt.13
## 1 1 1 1
## euloph.17 torymi.1 thynni.4 hymeno.12
## 1 1 1 1
## euloph.15 pterom.6 tricho.2 encyrt.11
## 1 1 1 1
## signip.2 apheli.4 psyllo.2 aphel.5
## 1 1 1 1
## bethyl.9 bethyl.8 crabro.16 pompil.2
## 1 1 1 1
## cleonym.1 encyrt.7 apheli.3 encyrt.8
## 1 1 1 1
## euloph.11 euloph.10 euloph.8 formic.18
## 1 1 1 1
## chalci.7 chaobo.1 encyrt.6 mutill.3
## 1 1 1 1
## crabro.12 gaster.1 euloph.6 bethyl.5
## 1 1 1 1
## crabro.8 encyrt.1 chalci.5 formic.17
## 1 1 1 1
## ormyri.1 bracon.10 perila.2 thynnid.0
## 1 1 1 1
## bracon.9 bracon.6 bethyl.4 halict.12
## 1 1 1 1
## chalci.3 bethyl.3 chrysi.2 formic.10
## 1 1 1 1
## bethyl.2 bethyl.1 formic.7 hymeno.1
## 1 1 1 1
## chalci.1 chrysi.1 halict.4 halict.8
## 1 1 1 1
## pompil.1 culici.2 drosop.5 tachin.3
## 1 1 1 1
## asilid.4 ephydr.1 syrphi.2 syrphi.1
## 1 1 1 1
## psycho.1 muscid.8 dipter.18 cerato.8
## 1 1 1 1
## dolich.3 bombyl.7 aleyro.3 aphodi.1
## 1 1 1 1
## lauxan.1 rhinii.4 chaobo.2 chiron.2
## 1 1 1 1
## dipter.17 phorid.5 culici.1 ceraph.3
## 1 1 1 1
## cecido.4 bombyl.4 milich.10 calliph.1
## 1 1 1 1
## myceto.1 tephri.1 carnid.1 oestri.1
## 1 1 1 1
## milich.8 ephydr.3 cecido.3 cecido.2
## 1 1 1 1
## dolich.1 sarcop.3 sepsid.3 cerato.4
## 1 1 1 1
## sarcop.1 milich.1 mythic.2 coreth.1
## 1 1 1 1
## cicade.8 delpha.3 mirida.8 mirida.7
## 1 1 1 1
## insect.5 kinnar.1 phlaeo.12 phlaeo.11
## 1 1 1 1
## aphido.2 betida.1 cicade.6 phlaeo.10
## 1 1 1 1
## psocop.3 beryti.1 delpha.2 delpha.1
## 1 1 1 1
## sternoryncha psocop.2 phlaeo.7 insect.3
## 1 1 1 1
## cicado.1 nevrop.1 phlaeo.3 meloid.7
## 1 1 1 0
## meloid.6 meloid.5 chryso.7 bethyl.5.1
## 0 0 0 0
## heterog.1 formic.16 bombyl.9 ulidii.1
## 0 0 0 0
## insect.4
## 0
Tableau
test0
## morphotype famille ordre superfam fipiabu
## 1 leiodi.1 Leiodidae Coleoptera Staphylinoidea 1
## 2 culici.2 Culicidae Diptera Culicoidea 1
## 3 crabro.21 Crabronidae Hymenoptera Apoidea 1
## 4 formic.21 Formicidae Hymenoptera Formicoidea 1
## 5 crabro.20 Crabronidae Hymenoptera Apoidea 1
## 6 pompil.5 Pompilidae Hymenoptera Pompiloidea 2
## 7 bombyl.9 Bombylidae Diptera Asiloidea 0
## 8 chamae.1 Chamaemyiidae Diptera Lauxanioidea 2
## 9 euloph.18 Eulophidae Hymenoptera Chalcidoidea 1
## 10 formic.20 Formicidae Hymenoptera Formicoidea 2
## 11 coccin.7 Coccinelidae Coleoptera Cucujoidea 1
## 12 cicade.8 Cicadellidae Hemiptera Membracoidea 1
## 13 chloro.11 Chloropidae Diptera Carnoidea 2
## 14 bracon.14 Braconidae Hymenoptera Ichneumonoidea 4
## 15 delpha.3 Delphacidae Hemiptera Fulgoroidea 1
## 16 mirida.8 Miridae Hemiptera Lygaeoidea 1
## 17 mirida.7 Miridae Hemiptera Lygaeoidea 1
## 18 drosop.5 Drosophilidae Diptera Ephydroidea 1
## 19 pterom.9 Pteromalidae Hymenoptera Chalcidoidea 1
## 20 tachin.3 Tachinidae Diptera Oestroidea 1
## 21 tetrac.8 Tetracampidae Hymenoptera Chalcidoidea 1
## 22 encyrt.16 Encyrtidae Hymenoptera Chalcidoidea 1
## 23 ichneu.3 Ichneumonidae Hymenoptera Ichneumonoidea 1
## 24 rhaphi.1 Rhaphidophoridae Orthoptera Rhaphidophoroidea 2
## 25 asilid.4 Asilidae Diptera Asiloidea 1
## 26 cicade.7 Cicadellidae Hemiptera Membracoidea 5
## 27 crabro.18 Crabronidae Hymenoptera Apoidea 1
## 28 pterom.8 Pteromalidae Hymenoptera Chalcidoidea 1
## 29 chryso.13 Chrysomelidae Coleoptera Chrysomeloidea 2
## 30 ephydr.1 Ephrydridae Diptera Ephydroidea 1
## 31 syrphi.2 Syrphidae Diptera Syrphoidea 1
## 32 insect.5 Insecta 1
## 33 psocop.4 Psocoptera 4
## 34 ptinid.1 Ptinidae Coleoptera Bostrichoidea 6
## 35 halict.19 Halictidae Hymenoptera Apoidea 2
## 36 anthoc.1 Anthocoridae Hemiptera Cimicoidea 2
## 37 kinnar.1 Kinnaridae Hemiptera Fulgoroidea 1
## 38 liopte.1 Liopteridae Hymenoptera 3
## 39 syrphi.1 Syrphidae Diptera Syrphoidea 1
## 40 bethyl.11 Bethylidae Hymenoptera Chrysidoidea 1
## 41 encyrt.15 Encyrtidae Hymenoptera Chalcidoidea 1
## 42 encyrt.14 Encyrtidae Hymenoptera Chalcidoidea 1
## 43 phlaeo.12 Phlaeotripidae Thysanoptera Tubulifera 1
## 44 phlaeo.11 Phlaeotripidae Thysanoptera Tubulifera 1
## 45 aphido.2 Aphidoidae Hemiptera Aphidoidea 1
## 46 psycho.1 Psychodidae Diptera Psychodoidea 1
## 47 chryso.6 Chrysomelidae Coleoptera Chrysomeloidea 2
## 48 lepido.7 Lepidoptera 4
## 49 eupelm.14 Eupelmidae Hymenoptera Chalcidoidea 2
## 50 muscid.8 Muscidae Diptera Muscoidea 1
## 51 loncha.2 Lonchaeidae Diptera Lonchaeoidea 4
## 52 muscid.7 Muscidae Diptera Muscoidea 6
## 53 acrid.1 Acrididae Orthoptera Acridoidea 4
## 54 staphy.3 Staphylinidae Coleoptera Staphylinoidea 4
## 55 andren.1 Andrenidae Hymenoptera Apoidea 1
## 56 dryini.1 Dryinididae Hymenoptera Chrysidoidea 1
## 57 dipter.18 Diptera 1
## 58 cerato.8 Ceratopogonidae Diptera Chironomoidea 1
## 59 dolich.3 Dolichopodidae Diptera Empidoidea 1
## 60 bethyl.10 Bethylidae Hymenoptera Chrysidoidea 2
## 61 bombyl.7 Bombylidae Diptera Asiloidea 1
## 62 coccin.6 Coccinelidae Coleoptera Cucujoidea 3
## 63 chiron.3 Chironomidae Diptera Chironomoidea 2
## 64 cecido.8 Cecidomyiidae Diptera Sciaroidea 7
## 65 cecido.7 Cecidomyiidae Diptera Sciaroidea 3
## 66 aleyro.3 Aleyroionidae Hemiptera Aleyrodoidea 1
## 67 bombyl.6 Bombylidae Diptera Asiloidea 8
## 68 betida.1 Baetidae Ephemeroptera Baetoidea 1
## 69 pterom.7 Pteromalidae Hymenoptera Chalcidoidea 1
## 70 chrysol.2 Chrysolampidae Hymenoptera Chalcidoidea 17
## 71 cerylo.1 Cerylonidae Coleoptera Cucujoidea 1
## 72 aphodi.1 Aphodiidae Coleoptera Scarabaeoidea 1
## 73 chloro.9 Chloropidae Diptera Carnoidea 7
## 74 ceraph.4 Ceraphronidae Hymenoptera Ceraphronoidea 1
## 75 cecido.6 Cecidomyiidae Diptera Sciaroidea 5
## 76 diapar.1 Diapriidae Hymenoptera Diaprioidea 1
## 77 lauxan.1 Lauxaniidae Diptera Lauxanioidea 1
## 78 thynni.5 Thynnidae Hymenoptera Thynnoidea 2
## 79 rhinop.1 Rhinophoridae Diptera Oestroidea 113
## 80 muscid.4 Muscidae Diptera Muscoidea 4
## 81 achili.1 Achilidae Hemiptera Fulgoroidea 3
## 82 rhinii.4 Rhiniidae Diptera Oestroidea 1
## 83 bombyl.5 Bombylidae Diptera Asiloidea 3
## 84 chaobo.2 Chaoboridae Diptera Culicoidea 1
## 85 euloph.16 Eulophidae Hymenoptera Chalcidoidea 1
## 86 eutric.1 Eutrichosomatidae Hymenoptera Chalcidoidea 1
## 87 cicade.6 Cicadellidae Hemiptera Membracoidea 1
## 88 chiron.2 Chironomidae Diptera Chironomoidea 1
## 89 apsilo.1 Apsilocephalidae Diptera Asiloidea 3
## 90 pompil.4 Pompilidae Hymenoptera Pompiloidea 1
## 91 phlaeo.10 Phlaeotripidae Thysanoptera Tubulifera 1
## 92 lepido.6 Lepidoptera 7
## 93 dipter.17 Diptera 1
## 94 chiron.1 Chironomidae Diptera Chironomoidea 7
## 95 phorid.5 Phoridae Diptera Platypezoidea 1
## 96 psocop.3 Psocoptera 1
## 97 culici.1 Culicidae Diptera Culicoidea 1
## 98 lepido.5 Lepidoptera 2
## 99 halict.18 Halictidae Hymenoptera Apoidea 2
## 100 ceraph.3 Ceraphronidae Hymenoptera Ceraphronoidea 1
## 101 dolich.2 Dolichopodidae Diptera Empidoidea 7
## 102 betyhl.7 Bethylidae Hymenoptera Chrysidoidea 1
## 103 scolii.3 Scoliidae Hymenoptera Vespoidea 1
## 104 encyrt.13 Encyrtidae Hymenoptera Chalcidoidea 1
## 105 dermes.4 Dermestidae Coleoptera Bostrichoidea 3
## 106 euloph.17 Eulophidae Hymenoptera Chalcidoidea 1
## 107 bracon.13 Braconidae Hymenoptera Ichneumonoidea 23
## 108 torymi.1 Torymidae Hymenoptera Chalcidoidea 1
## 109 thynni.4 Thynnidae Hymenoptera Thynnoidea 1
## 110 chrysol.1 Chrysolampidae Hymenoptera Chalcidoidea 10
## 111 hymeno.12 Hymenoptera 1
## 112 euloph.15 Eulophidae Hymenoptera Chalcidoidea 1
## 113 pterom.6 Pteromalidae Hymenoptera Chalcidoidea 1
## 114 tricho.2 Trichogrammatidae Hymenoptera Chalcidoidea 1
## 115 encyrt.11 Encyrtidae Hymenoptera Chalcidoidea 1
## 116 euloph.14 Eulophidae Hymenoptera Chalcidoidea 6
## 117 eupelm.12 Eupelmidae Hymenoptera Chalcidoidea 14
## 118 tephri.4 Tephritidae Diptera Tephritoidea 2
## 119 signip.2 Signiphoridae Hymenoptera Chalcidoidea 1
## 120 signip.1 Signiphoridae Hymenoptera Chalcidoidea 3
## 121 apheli.4 Aphelinidae Hymenoptera Chalcidoidea 1
## 122 formic.19 Formicidae Hymenoptera Formicoidea 3
## 123 psyllo.2 Hemiptera 1
## 124 eupelm.13 Eupelmidae Hymenoptera Chalcidoidea 2
## 125 cecido.4 Cecidomyiidae Diptera Sciaroidea 1
## 126 coniop.2 Coniopterigydae Neuroptera Coniopterygoidea 4
## 127 aphel.5 Aphelinidae Hymenoptera Chalcidoidea 1
## 128 tetrac.7 Tetracampidae Hymenoptera Chalcidoidea 3
## 129 bombyl.4 Bombylidae Diptera Asiloidea 1
## 130 euloph.13 Eulophidae Hymenoptera Chalcidoidea 3
## 131 platyg.4 Platygastridae Hymenoptera Platygastroidea 5
## 132 bethyl.9 Bethylidae Hymenoptera Chrysidoidea 1
## 133 bethyl.8 Bethylidae Hymenoptera Chrysidoidea 1
## 134 milich.10 Milichiidae Diptera Carnoidea 1
## 135 crabro.16 Crabronidae Hymenoptera Apoidea 1
## 136 crabro.15 Crabronidae Hymenoptera Apoidea 3
## 137 pompil.3 Pompilidae Hymenoptera Pompiloidea 2
## 138 pompil.2 Pompilidae Hymenoptera Pompiloidea 1
## 139 calliph.1 Calliphoridae Diptera Oestroidea 1
## 140 cleonym.1 Cleonymidae Hymenoptera Chalcidoidea 1
## 141 perila.4 Perilampidae Hymenoptera Chalcidoidea 2
## 142 crabro.17 Crabronidae Hymenoptera Apoidea 2
## 143 beryti.1 Berytidae Hemiptera Lygaeoidea 1
## 144 encyrt.7 Encyrtidae Hymenoptera Chalcidoidea 1
## 145 apheli.3 Aphelinidae Hymenoptera Chalcidoidea 1
## 146 apheli.2 Aphelinidae Hymenoptera Chalcidoidea 2
## 147 myceto.1 Mycetophilidae Diptera Sciaroidea 1
## 148 encyrt.8 Encyrtidae Hymenoptera Chalcidoidea 1
## 149 cerato.7 Ceratopogonidae Diptera Chironomoidea 4
## 150 euloph.12 Eulophidae Hymenoptera Chalcidoidea 4
## 151 euloph.11 Eulophidae Hymenoptera Chalcidoidea 1
## 152 euloph.10 Eulophidae Hymenoptera Chalcidoidea 1
## 153 pterom.4 Pteromalidae Hymenoptera Chalcidoidea 2
## 154 euloph.9 Eulophidae Hymenoptera Chalcidoidea 3
## 155 euloph.8 Eulophidae Hymenoptera Chalcidoidea 1
## 156 cerato.6 Ceratopogonidae Diptera Chironomoidea 16
## 157 tephri.1 Tephritidae Diptera Tephritoidea 1
## 158 euryto.3 Eurytomidae Hymenoptera Chalcidoidea 5
## 159 encyrt.9 Encyrtidae Hymenoptera Chalcidoidea 2
## 160 nitidu.1 Nitidulidae Coleoptera Cucujoidea 1
## 161 encyrt.10 Encyrtidae Hymenoptera Chalcidoidea 2
## 162 platyg.3 Platygastridae Hymenoptera Platygastroidea 7
## 163 mythic.8 Mythicomyiidae Diptera Asiloidea 5
## 164 mythic.7 Mythicomyiidae Diptera Asiloidea 7
## 165 formic.18 Formicidae Hymenoptera Formicoidea 1
## 166 carnid.1 Carnidae Diptera Carnoidea 1
## 167 chalci.7 Chalcididae Hymenoptera Chalcidoidea 1
## 168 mymari.1 Mymaridae Hymenoptera Chalcidoidea 2
## 169 tricho.1 Trichogrammatidae Hymenoptera Chalcidoidea 2
## 170 phlaeo.8 Phlaeotripidae Thysanoptera Tubulifera 5
## 171 phlaeo.9 Phlaeotripidae Thysanoptera Tubulifera 9
## 172 eupelm.11 Eupelmidae Hymenoptera Chalcidoidea 4
## 173 chaobo.1 Chaoboridae Diptera Culicoidea 1
## 174 pterom.5 Pteromalidae Hymenoptera Chalcidoidea 3
## 175 bracon.12 Braconidae Hymenoptera Ichneumonoidea 5
## 176 encyrt.6 Encyrtidae Hymenoptera Chalcidoidea 1
## 177 encyrt.5 Encyrtidae Hymenoptera Chalcidoidea 2
## 178 encyrt.3 Encyrtidae Hymenoptera Chalcidoidea 4
## 179 encyrt.4 Encyrtidae Hymenoptera Chalcidoidea 5
## 180 ormyri.2 Ormyridae Hymenoptera Chalcidoidea 6
## 181 euloph.7 Eulophidae Hymenoptera Chalcidoidea 6
## 182 crypto.1 Cryptochetidae Diptera Lonchaeoidea 4
## 183 euryto.2 Eurytomidae Hymenoptera Chalcidoidea 5
## 184 oestri.1 Oestridae Diptera Oestridae 1
## 185 coniop.1 Coniopterigydae Neuroptera Coniopterygoidea 5
## 186 mutill.3 Mutillidae Hymenoptera Pompiloidea 1
## 187 crabro.14 Crabronidae Hymenoptera Apoidea 4
## 188 crabro.13 Crabronidae Hymenoptera Apoidea 13
## 189 dermes.3 Dermestidae Coleoptera Bostrichoidea 4
## 190 milich.8 Milichiidae Diptera Carnoidea 1
## 191 neurop.2 Chrysopidae Neuroptera Chrysopoidea 2
## 192 ephydr.3 Ephrydridae Diptera Ephydroidea 1
## 193 mirida.6 Miridae Hemiptera Lygaeoidea 22
## 194 cicade.5 Cicadellidae Hemiptera Membracoidea 65
## 195 crabro.12 Crabronidae Hymenoptera Apoidea 1
## 196 chryso.12 Chrysomelidae Coleoptera Chrysomeloidea 2
## 197 chloro.8 Chloropidae Diptera Carnoidea 2
## 198 eupelm.10 Eupelmidae Hymenoptera Chalcidoidea 2
## 199 muscid.6 Muscidae Diptera Muscoidea 7
## 200 muscid.5 Muscidae Diptera Muscoidea 4
## 201 odinii.1 Odiniidae Diptera Opomyzoidea 2
## 202 hymeno.8 Hymenoptera 2
## 203 platyg.2 Platygastridae Hymenoptera Platygastroidea 16
## 204 gaster.1 Gasteruptiidae Hymenoptera Evanioidea 1
## 205 delpha.2 Delphacidae Hemiptera Fulgoroidea 1
## 206 cicade.4 Cicadellidae Hemiptera Membracoidea 2
## 207 mordel.1 Mordellidae Coleoptera Tenebrionoidea 6
## 208 delpha.1 Delphacidae Hemiptera Fulgoroidea 1
## 209 encyrt.2 Encyrtidae Hymenoptera Chalcidoidea 2
## 210 loncha.1 Lonchaeidae Diptera Lonchaeoidea 7
## 211 anthom.1 Anthomyiidae Diptera Muscoidea 2
## 212 eupelm.8 Eupelmidae Hymenoptera Chalcidoidea 2
## 213 aphido.1 Aphidoidae Hemiptera Aphidoidea 46
## 214 lepido.4 Lepidoptera 5
## 215 cicade.3 Cicadellidae Hemiptera Membracoidea 14
## 216 chloro.6 Chloropidae Diptera Carnoidea 8
## 217 rhinii.3 Rhiniidae Diptera Oestroidea 2
## 218 rhinii.2 Rhiniidae Diptera Oestroidea 3
## 219 platyg.1 Platygastridae Hymenoptera Platygastroidea 36
## 220 euloph.6 Eulophidae Hymenoptera Chalcidoidea 1
## 221 crabro.10 Crabronidae Hymenoptera Apoidea 2
## 222 bethyl.5 Bethylidae Hymenoptera Chrysidoidea 1
## 223 chloro.5 Chloropidae Diptera Carnoidea 18
## 224 crabro.9 Crabronidae Hymenoptera Apoidea 3
## 225 drosop.4 drosophilidae Diptera Ephydroidea 5
## 226 crabro.8 Crabronidae Hymenoptera Apoidea 1
## 227 muscid.3 Muscidae Diptera Muscoidea 5
## 228 encyrt.1 Encyrtidae Hymenoptera Chalcidoidea 1
## 229 cecido.3 Cecidomyiidae Diptera Sciaroidea 1
## 230 cicade.2 Cicadellidae Hemiptera Membracoidea 2
## 231 bracon.11 Braconidae Hymenoptera Ichneumonoidea 2
## 232 apheli.1 Aphelinidae Hymenoptera Chalcidoidea 2
## 233 sternoryncha Hemiptera 1
## 234 aleyro.2 Aleyrodidae Hemiptera Aleyrodoidea 2
## 235 mythic.5 Mythicomyiidae Diptera Asiloidea 17
## 236 chalci.5 Chalcididae Hymenoptera Chalcidoidea 1
## 237 coccin.5 Coccinelidae Coleoptera Cucujoidea 6
## 238 psocop.2 Psocoptera 1
## 239 formic.17 Formicidae Hymenoptera Formicoidea 1
## 240 chryso.8 Chrysomelidae Coleoptera Chrysomeloidea 1
## 241 dipter.15 Diptera 2
## 242 ormyri.1 Ormyridae Hymenoptera Chalcidoidea 1
## 243 milich.5 Milichiidae Diptera Carnoidea 15
## 244 cecido.2 Cecidomyiidae Diptera Sciaroidea 1
## 245 phlaeo.7 Phlaeotripidae Thysanoptera Tubulifera 1
## 246 meloid.7 Meloidae Coleoptera Tenebrionoidea 0
## 247 meloid.6 Meloidae Coleoptera Tenebrionoidea 0
## 248 meloid.5 Meloidae Coleoptera Tenebrionoidea 0
## 249 chryso.7 Chrysomelidae Coleoptera Chrysomeloidea 0
## 250 meloid.4 Meloidae Coleoptera Tenebrionoidea 1
## 251 bethyl.5 Bethylidae Hymenoptera Chrysidoidea 1
## 252 tetrac.5 Tetracampidae Hymenoptera Chalcidoidea 5
## 253 eupelm.5 Eupelmidae Hymenoptera Chalcidoidea 2
## 254 mutill.2 Mutillidae Hymenoptera Pompiloidea 3
## 255 heterog.1 Heterogynaidae Hymenoptera Apoidea 0
## 256 insect.4 Hemiptera 0
## 257 bracon.10 Braconidae Hymenoptera Ichneumonoidea 1
## 258 asilid.3 Asilidae Diptera Asiloidea 2
## 259 insect.3 Hemiptera 1
## 260 carabi.4 Carabidae Coleoptera Caraboidea 2
## 261 hemipt.2 Hemiptera 5
## 262 dolich.1 Dolichopodidae Diptera Empidoidea 1
## 263 hemipt.1 Hemiptera 2
## 264 cicado.1 Hemiptera 1
## 265 halict.17 Halictidae Hymenoptera Apoidea 62
## 266 asilid.2 Asilidae Diptera Asiloidea 2
## 267 phlaeo.6 Phlaeotripidae Thysanoptera Tubulifera 14
## 268 coleop.2 Coleoptera 2
## 269 perila.2 Perilampidae Hymenoptera Chalcidoidea 1
## 270 eupelm.4 Eupelmidae Hymenoptera Chalcidoidea 5
## 271 apidae.5 Apidae Hymenoptera Apoidea 2
## 272 thynnid.0 Thynnidae Hymenoptera Thynnoidea 1
## 273 bracon.9 Braconidae Hymenoptera Ichneumonoidea 1
## 274 euloph.5 Eulophidae Hymenoptera Chalcidoidea 11
## 275 staphy.2 Staphylinidae Coleoptera Staphylinoidea 1
## 276 bracon.8 Braconidae Hymenoptera Ichneumonoidea 5
## 277 phlaeo.5 Phlaeotripidae Thysanoptera Tubulifera 3
## 278 euryto.1 Eurytomidae Hymenoptera Chalcidoidea 11
## 279 eupelm.3 Eupelmidae Hymenoptera Chalcidoidea 5
## 280 meloid.3 Meloidae Coleoptera Tenebrionoidea 4
## 281 milich.4 Milichiidae Diptera Carnoidea 3
## 282 sarcop.3 Sarcophagidae Diptera Oestroidea 1
## 283 sepsid.3 Sepsidae Diptera Sciomyzoidea 1
## 284 cerato.4 Ceratopogonidae Diptera Chironomoidea 1
## 285 lepido.3 Lepidoptera 3
## 286 nevrop.1 Coniopterigydae Neuroptera Coniopterygoidea 1
## 287 chloro.4 Chloropidae Diptera Carnoidea 10
## 288 bracon.7 Braconidae Hymenoptera Ichneumonoidea 13
## 289 coccin.4 Coccinelidae Coleoptera Cucujoidea 3
## 290 aleyro.1 Aleyrodidae Hemiptera Aleyrodoidea 35
## 291 bracon.6 Braconidae Hymenoptera Ichneumonoidea 1
## 292 bethyl.4 Bethylidae Hymenoptera Chrysidoidea 1
## 293 tetrac.3 Tetracampidae Hymenoptera Chalcidoidea 2
## 294 asilid.1 Asilidae Diptera Asiloidea 3
## 295 sarcop.2 Sarcophagidae Diptera Oestroidea 5
## 296 formic.16 Formicidae Hymenoptera Formicoidea 0
## 297 hymeno.3 Hymenoptera 2
## 298 chalci.4 Chalcididae Hymenoptera Chalcidoidea 2
## 299 sarcop.1 Sarcophagidae Diptera Oestroidea 1
## 300 formic.15 Formicidae Hymenoptera Formicoidea 2
## 301 bracon.5 Braconidae Hymenoptera Ichneumonoidea 5
## 302 ulidii.1 Ulidiidae Diptera Tephritoidea 0
## 303 halict.12 Halictidae Hymenoptera Apoidea 1
## 304 dipter.13 Diptera 2
## 305 formic.14 Formicidae Hymenoptera Formicoidea 10
## 306 apidae.6 Apidae Hymenoptera Apoidea 3
## 307 cerato.3 Ceratopogonidae Diptera Chironomoidea 2
## 308 chalci.3 Chalcididae Hymenoptera Chalcidoidea 1
## 309 euloph.4 Eulophidae Hymenoptera Chalcidoidea 22
## 310 pterom.10 Pteromalidae Hymenoptera Chalcidoidea 4
## 311 cecido.1 Cecidomyiidae Diptera Sciaroidea 3
## 312 milich.1 Milichiidae Diptera Carnoidea 1
## 313 formic.13 Formicidae Hymenoptera Formicoidea 50
## 314 bethyl.3 Bethylidae Hymenoptera Chrysidoidea 1
## 315 cerato.1 Ceratopogonidae Diptera Chironomoidea 10
## 316 chryso.5 Chrysomelidae Coleoptera Chrysomeloidea 5
## 317 chalci.2 Chalcididae Hymenoptera Chalcidoidea 9
## 318 chryso.4 Chrysomelidae Coleoptera Chrysomeloidea 16
## 319 euloph.3 Eulophidae Hymenoptera Chalcidoidea 3
## 320 coccin.3 Coccinelidae Coleoptera Cucujoidea 4
## 321 eupelm.2 Eupelmidae Hymenoptera Chalcidoidea 22
## 322 dermes.2 Dermestidae Coleoptera Bostrichoidea 4
## 323 chryso.3 Chrysomelidae Coleoptera Chrysomeloidea 27
## 324 chrysi.2 Chrysididae Hymenoptera Chrysidoidea 1
## 325 formic.8 Formicidae Hymenoptera Formicoidea 264
## 326 bupres.2 Buprestidae Coleoptera Buprestoidea 5
## 327 formic.12 Formicidae Hymenoptera Formicoidea 2
## 328 formic.11 Formicidae Hymenoptera Formicoidea 2
## 329 formic.10 Formicidae Hymenoptera Formicoidea 1
## 330 tachin.1 Tachinidae Diptera Oestroidea 15
## 331 mythic.3 Mythicomyiidae Diptera Asiloidea 154
## 332 phorid.4 Phoridae Diptera Platypezoidea 20
## 333 phorid.3 Phoridae Diptera Platypezoidea 16
## 334 perila.1 Perilampidae Hymenoptera Chalcidoidea 8
## 335 megasp.1 Megaspilidae Hymenoptera Ceraphronoidea 4
## 336 phorid.2 Phoridae Diptera Platypezoidea 81
## 337 mythic.2 Mythicomyiidae Diptera Asiloidea 1
## 338 tingid.1 Tingidae Hemiptera Miroidea 3
## 339 chloro.3 Chloropidae Diptera Carnoidea 27
## 340 pterom.1(platyg) Pteromalidae Hymenoptera Chalcidoidea 5
## 341 coreth.1 Corethrellidae Diptera Culicoidea 1
## 342 muscid.2 Muscidae Diptera Muscoidea 4
## 343 bracon.4 Braconidae Hymenoptera Ichneumonoidea 31
## 344 lepido.2 Lepidoptera 3
## 345 bethyl.2 Bethylidae Hymenoptera Chrysidoidea 1
## 346 formic.9 Formicidae Hymenoptera Formicoidea 2
## 347 bethyl.1 Bethylidae Hymenoptera Chrysidoidea 1
## 348 eupelm.1 Eupelmidae Hymenoptera Chalcidoidea 5
## 349 formic.7 Formicidae Hymenoptera Formicoidea 1
## 350 lepido.1 Lepidoptera 97
## 351 phorid.1 Phoridae Diptera Platypezoidea 6
## 352 mythic.1 Mythicomyiidae Diptera Asiloidea 3
## 353 mythic.4 Mythicomyiidae Diptera Asiloidea 8
## 354 cicade.1 Cicadellidae Hemiptera Membracoidea 5
## 355 bombyl.2 Bombylidae Diptera Asiloidea 18
## 356 formic.6 Formicidae Hymenoptera Formicoidea 5
## 357 coccin.1 Coccinelidae Coleoptera Cucujoidea 14
## 358 coccin.2 Coccinelidae Coleoptera Cucujoidea 4
## 359 chloro.1 Chloropidae Diptera Carnoidea 42
## 360 chloro.2 Chloropidae Diptera Carnoidea 17
## 361 formic.3 Formicidae Hymenoptera Formicoidea 21
## 362 bupres.1 Buprestidae Coleoptera Buprestoidea 8
## 363 chryso.2 Chrysomelidae Coleoptera Chrysomeloidea 1
## 364 curcul.1 Curculionidae Coleoptera Curculionoidea 10
## 365 curcul.2 Curculionidae Coleoptera Curculionoidea 4
## 366 dermes.1 Dermestidae Coleoptera Bostrichoidea 7
## 367 elater.1 Elateridae Coleoptera Elateroidea 1
## 368 hymeno.1 Hymenoptera 1
## 369 lycida.1 Lycidae Coleoptera Cantharoidea 1
## 370 muscid.1 Muscidae Diptera Muscoidea 61
## 371 meloid.1 Meloidae Coleoptera Tenebrionoidea 9
## 372 meloid.2 Meloidae Coleoptera Tenebrionoidea 20
## 373 drosop.1 Drosophilidae Diptera Ephydroidea 2
## 374 mirida.2 Miridae Hemiptera Lygaeoidea 11
## 375 mirida.1 Miridae Hemiptera Lygaeoidea 3
## 376 apidae.1 Apidae Hymenoptera Apoidea 2
## 377 bracon.1 Braconidae Hymenoptera Ichneumonoidea 100
## 378 chalci.1 Chalcididae Hymenoptera Chalcidoidea 1
## 379 chrysi.1 Chrysididae Hymenoptera Chrysidoidea 1
## 380 crabro.2 Crabronidae Hymenoptera Apoidea 6
## 381 crabro.3 Crabronidae Hymenoptera Apoidea 8
## 382 crabro.4 Crabronidae Hymenoptera Apoidea 17
## 383 euloph.2 Eulophidae Hymenoptera Chalcidoidea 5
## 384 euloph.1 Eulophidae Hymenoptera Chalcidoidea 9
## 385 formic.1 Formicidae Hymenoptera Formicoidea 204
## 386 formic.2 Formicidae Hymenoptera Formicoidea 10
## 387 formic.4 Formicidae Hymenoptera Formicoidea 34
## 388 halict.1 Halictidae Hymenoptera Apoidea 5
## 389 halict.2 Halictidae Hymenoptera Apoidea 26
## 390 halict.3 Halictidae Hymenoptera Apoidea 162
## 391 halict.4 Halictidae Hymenoptera Apoidea 1
## 392 halict.8 Halictidae Hymenoptera Apoidea 1
## 393 ichneu.1 Ichneumonididae Hymenoptera Ichneumonoidea 2
## 394 pompil.1 Pompilidae Hymenoptera Pompiloidea 1
## 395 scolii.1 Scoliidae Hymenoptera Vespoidea 2
## 396 scolii.2 Scoliidae Hymenoptera Vespoidea 3
## 397 thynni.1 Thynnidae Hymenoptera Thynnoidea 10
## 398 thynni.2 Thynnidae Hymenoptera Thynnoidea 6
## 399 phlaeo.1 Phlaeotripidae Thysanoptera Tubulifera 25
## 400 phlaeo.3 Phlaeotripidae Thysanoptera Tubulifera 1
## 401 phlaeo.4 Phlaeotripidae Thysanoptera Tubulifera 101
test0bis<-subset(test0,test0$fipiabu != 0)
unique(test0$morphotype[test0$superfam=="Tephritoidea"])
## [1] "tephri.4" "tephri.1" "ulidii.1"
unique(test0bis$morphotype[test0bis$ordre=="Diptera"])
## [1] "culici.2" "chamae.1" "chloro.11" "drosop.5" "tachin.3" "asilid.4"
## [7] "ephydr.1" "syrphi.2" "syrphi.1" "psycho.1" "muscid.8" "loncha.2"
## [13] "muscid.7" "dipter.18" "cerato.8" "dolich.3" "bombyl.7" "chiron.3"
## [19] "cecido.8" "cecido.7" "bombyl.6" "chloro.9" "cecido.6" "lauxan.1"
## [25] "rhinop.1" "muscid.4" "rhinii.4" "bombyl.5" "chaobo.2" "chiron.2"
## [31] "apsilo.1" "dipter.17" "chiron.1" "phorid.5" "culici.1" "dolich.2"
## [37] "tephri.4" "cecido.4" "bombyl.4" "milich.10" "calliph.1" "myceto.1"
## [43] "cerato.7" "cerato.6" "tephri.1" "mythic.8" "mythic.7" "carnid.1"
## [49] "chaobo.1" "crypto.1" "oestri.1" "milich.8" "ephydr.3" "chloro.8"
## [55] "muscid.6" "muscid.5" "odinii.1" "loncha.1" "anthom.1" "chloro.6"
## [61] "rhinii.3" "rhinii.2" "chloro.5" "drosop.4" "muscid.3" "cecido.3"
## [67] "mythic.5" "dipter.15" "milich.5" "cecido.2" "asilid.3" "dolich.1"
## [73] "asilid.2" "milich.4" "sarcop.3" "sepsid.3" "cerato.4" "chloro.4"
## [79] "asilid.1" "sarcop.2" "sarcop.1" "dipter.13" "cerato.3" "cecido.1"
## [85] "milich.1" "cerato.1" "tachin.1" "mythic.3" "phorid.4" "phorid.3"
## [91] "phorid.2" "mythic.2" "chloro.3" "coreth.1" "muscid.2" "phorid.1"
## [97] "mythic.1" "mythic.4" "bombyl.2" "chloro.1" "chloro.2" "muscid.1"
## [103] "drosop.1"
test0 %>%
filter(ordre %in% c("Coleoptera", "Diptera", "Hymenoptera", "Hemiptera")) %>%
ggplot() +
aes(x = superfam, y = fipiabu, fill = ordre) +
geom_col() +
scale_fill_hue(direction = 1) +
theme_minimal()
#Pollinisateurs
poll = subset(test0, superfam == "Apoidea"
| famille == "Chrysididae" | famille == "Bombylidae" | famille == "Mythicomyiidae"| famille == "Chloropidae" | famille == "Syrphidae" | famille == "Sepsidae"|famille=="Pompilidae"|famille == "Sepsidae"|famille=="Buprestidae" |famille=="Dermestidae"|famille=="Lycidae"|famille=="Scoliidae")
pollt<-t(poll$morphotype)
filetpoll<-filetall
piegepoll<-piegeall
fpollini<-select(filetpoll, Saison, identifiant_arbre, site, date, as.vector(pollt))
ppollini<-select(piegepoll, Saison, identifiant_arbre, site, date, as.vector(pollt))
Abondance pollinisateurs
fpollini$norga<-apply(fpollinix,1,sum)
fpollini$norga
## [1] 4 1 3 0 0 5 7 4 4 7 8 5 1 3 1 3 2 19 8 5 4 7 2 6 5
## [26] 6 20 4 4 2 42 21 35 23 12 40 16 9 10 21 10 25 2
ppollini$norga<-apply(ppollinix,1,sum)
ppollini$norga
## [1] 146 2 4 3 2 1 20 37 2 8 11 3 1 3 6 2 2 2 0
## [20] 4 15 0 43 1 4 1 3
Richesse spécifique pollinisateurs
l<-function(x){
x<-length(x[x!=0])
}
fpollini$rspe<-apply(fpollinix,1,l)
fpollini$rspe
## [1] 2 1 2 0 0 3 1 3 2 4 4 3 1 2 1 2 1 9 5 3 3 6 2 5 4
## [26] 5 14 4 3 2 10 7 8 6 6 5 5 6 5 7 5 4 2
ppollini$rspe<-apply(ppollinix,1,l)
ppollini$rspe
## [1] 5 2 2 1 1 1 2 8 2 3 8 3 1 3 4 1 1 2 0 4 5 0 4 1 4 1 3
syntfpoll<-subset(fpollini,select=c(Saison , identifiant_arbre,site,date, rspe, norga))
syntppoll<-subset(ppollini,select=c(Saison, identifiant_arbre,site,date, rspe, norga))
library(lme4)
syntfpoll<- mutate(syntfpoll, saison = as.factor(Saison),
site = as.factor(site))
syntfpoll<-left_join(syntfpoll,flor,by="identifiant_arbre")
syntppoll<- mutate(syntppoll, saison = as.factor(Saison),
site = as.factor(site))
syntppoll<-left_join(syntppoll,flor,by="identifiant_arbre")
library(ggplot2)
#Filet
colorpoll <- c("#333333","#FF6F00","#26A69A")
ggplot(syntfpoll, aes(x=Saison, y=rspe,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.4),aes(ymin=rspe-sd(rspe), ymax=rspe+sd(rspe)))+
theme_bw() + scale_color_manual(values=colorpoll) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.4)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +
ggtitle("Filet - Richesse spécifique") +
coord_cartesian(ylim = c(0, 15))+
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.4), : Ignoring unknown aesthetics: ymin and ymax
#Piege
ggplot(syntppoll, aes(x=Saison, y=rspe,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.4),aes(ymin=rspe-sd(rspe), ymax=rspe+sd(rspe)))+
theme_bw() + scale_color_manual(values=colorpoll) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.4)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +
ggtitle("Pieges - Richesse spécifique") +
coord_cartesian(ylim = c(0, 15))+
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.4), : Ignoring unknown aesthetics: ymin and ymax
#Filet
ggplot(syntfpoll, aes(x=Saison, y=norga,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.4),aes(ymin=norga-sd(norga), ymax=norga+sd(norga)))+
theme_bw() + scale_color_manual(values=colorpoll) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.4)) + labs(x = "Saison", y = "Abondance", fill="Site") +
ggtitle("Filet - Abondance") +
coord_cartesian(ylim = c(0,40))+
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.4), : Ignoring unknown aesthetics: ymin and ymax
#Piege
ggplot(syntppoll, aes(x=Saison, y=norga,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.4),aes(ymin=norga-sd(norga), ymax=norga+sd(norga)))+
theme_bw() + scale_color_manual(values=colorpoll) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.4)) + labs(x = "Saison", y = "Abondance", fill="Site") +
ggtitle("Pieges - Abondance") +
coord_cartesian(ylim = c(0, 150))+
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.4), : Ignoring unknown aesthetics: ymin and ymax
glmpol1<-glmer(rspe ~ site*Saison+(1|floraison), data = syntfpoll, family=poisson, nAGQ=2) #Estimation des paramètres du modèle par la Quadrature de Gauss-Hermite (Bolker, 2008)
## boundary (singular) fit: see help('isSingular')
summary(glmpol1)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * Saison + (1 | floraison)
## Data: syntfpoll
##
## AIC BIC logLik deviance df.resid
## 56.5 74.1 -18.3 36.5 33
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.1798 -0.5460 -0.1118 0.5422 2.8805
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 0 0
## Number of obs: 43, groups: floraison, 17
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.1632 0.2500 4.653 3.28e-06 ***
## siteExt_Reserve 0.7239 0.3046 2.376 0.0175 *
## siteReserve 0.1719 0.3393 0.506 0.6125
## SaisonFevrier 0.4463 0.3202 1.394 0.1633
## SaisonJuin -0.8267 0.4532 -1.824 0.0681 .
## siteExt_Reserve:SaisonFevrier -0.7929 0.4519 -1.755 0.0793 .
## siteReserve:SaisonFevrier 0.2202 0.4268 0.516 0.6059
## siteExt_Reserve:SaisonJuin -0.7239 0.6152 -1.177 0.2393
## siteReserve:SaisonJuin 0.5903 0.5698 1.036 0.3002
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv SsnFvr SasnJn sE_R:SF stR:SF sE_R:SJ
## sitExt_Rsrv -0.821
## siteReserve -0.737 0.605
## SaisonFevrr -0.781 0.641 0.575
## SaisonJuin -0.552 0.453 0.406 0.431
## stExt_Rs:SF 0.553 -0.674 -0.408 -0.708 -0.305
## stRsrv:SsnF 0.586 -0.481 -0.795 -0.750 -0.323 0.531
## stExt_Rs:SJ 0.406 -0.495 -0.299 -0.317 -0.737 0.334 0.238
## stRsrv:SsnJ 0.439 -0.360 -0.596 -0.343 -0.795 0.243 0.473 0.586
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')
Anova(glmpol1, type=3, method="chisq") #methode chis2 car glmer et type 3 car plan déséquilibré et présence d'une interaction
## Analysis of Deviance Table (Type III Wald chisquare tests)
##
## Response: rspe
## Chisq Df Pr(>Chisq)
## (Intercept) 21.6467 1 3.278e-06 ***
## site 7.0114 2 0.03003 *
## Saison 9.1622 2 0.01024 *
## site:Saison 9.1262 4 0.05802 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Test des résidus
library(DHARMa)
plot(simulateResiduals(glmpol1))
library(MuMIn) #Détermination du r2
r.squaredGLMM(glmpol1) #R2m représente le r avec seulement les effets fixes, et r2c il y a les effets de groupes
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## R2m R2c
## delta 0.5743682 0.5743682
## lognormal 0.6020896 0.6020896
## trigamma 0.5428376 0.5428376
#trigamma la plus fiable
TEST - PAIRWISE - Richesse spécifique - filet
emtpol1 <- lsmeans(glmpol1, ~ site, by="Saison")
pairs(emtpol1)
## Saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.724 0.305 Inf -2.376 0.0460
## (Bas-fond) - Reserve -0.172 0.339 Inf -0.506 0.8682
## Ext_Reserve - Reserve 0.552 0.288 Inf 1.917 0.1338
##
## Saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.069 0.334 Inf 0.207 0.9767
## (Bas-fond) - Reserve -0.392 0.259 Inf -1.514 0.2841
## Ext_Reserve - Reserve -0.461 0.314 Inf -1.469 0.3058
##
## Saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.000 0.535 Inf 0.000 1.0000
## (Bas-fond) - Reserve -0.762 0.458 Inf -1.665 0.2188
## Ext_Reserve - Reserve -0.762 0.458 Inf -1.665 0.2188
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
glmpol2<-glmer(rspe ~ site*Saison+(1|floraison), data = syntppoll, family=poisson, nAGQ=2) #Estimation des paramètres du modèle par la Quadrature de Gauss-Hermite (Bolker, 2008)
## boundary (singular) fit: see help('isSingular')
summary(glmpol2)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * Saison + (1 | floraison)
## Data: syntppoll
##
## AIC BIC logLik deviance df.resid
## 45.1 57.7 -12.5 25.1 16
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.7321 -0.7796 0.0000 0.5421 2.0000
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 0 0
## Number of obs: 26, groups: floraison, 16
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 8.473e-01 3.780e-01 2.242 0.025 *
## siteExt_Reserve 5.390e-01 4.756e-01 1.133 0.257
## siteReserve -1.130e-15 5.345e-01 0.000 1.000
## SaisonFevrier 1.335e-01 5.175e-01 0.258 0.796
## SaisonJuin -1.542e-01 5.563e-01 -0.277 0.782
## siteExt_Reserve:SaisonFevrier -6.035e-01 7.424e-01 -0.813 0.416
## siteReserve:SaisonFevrier 1.178e-01 7.224e-01 0.163 0.870
## siteExt_Reserve:SaisonJuin -1.232e+00 8.522e-01 -1.446 0.148
## siteReserve:SaisonJuin 9.163e-01 7.204e-01 1.272 0.203
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv SsnFvr SasnJn sE_R:SF stR:SF sE_R:SJ
## sitExt_Rsrv -0.795
## siteReserve -0.707 0.562
## SaisonFevrr -0.730 0.580 0.516
## SaisonJuin -0.679 0.540 0.480 0.496
## stExt_Rs:SF 0.509 -0.641 -0.360 -0.697 -0.346
## stRsrv:SsnF 0.523 -0.416 -0.740 -0.716 -0.355 0.499
## stExt_Rs:SJ 0.444 -0.558 -0.314 -0.324 -0.653 0.358 0.232
## stRsrv:SsnJ 0.525 -0.417 -0.742 -0.383 -0.772 0.267 0.549 0.504
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')
Anova(glmpol2, type=3, method="chisq") #methode chis2 car glmer et type 3 car plan déséquilibré et présence d'une interaction
## Analysis of Deviance Table (Type III Wald chisquare tests)
##
## Response: rspe
## Chisq Df Pr(>Chisq)
## (Intercept) 5.0254 1 0.02498 *
## site 1.8772 2 0.39118
## Saison 0.2842 2 0.86752
## site:Saison 8.1337 4 0.08680 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Test des résidus
library(DHARMa)
plot(simulateResiduals(glmpol2))
library(MuMIn) #Détermination du r2
r.squaredGLMM(glmpol2) #R2m représente le r avec seulement les effets fixes, et r2c il y a les effets de groupes
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## boundary (singular) fit: see help('isSingular')
## R2m R2c
## delta 0.3521363 0.3521363
## lognormal 0.3889913 0.3889913
## trigamma 0.3114272 0.3114272
#trigamma la plus fiable
TEST - PAIRWISE - Richesse spécifique - piege
emtpol3<- lsmeans(glmpol2, ~ site, by="Saison")
pairs(emtpol3)
## Saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.5390 0.476 Inf -1.133 0.4935
## (Bas-fond) - Reserve 0.0000 0.535 Inf 0.000 1.0000
## Ext_Reserve - Reserve 0.5390 0.476 Inf 1.133 0.4935
##
## Saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.0645 0.570 Inf 0.113 0.9930
## (Bas-fond) - Reserve -0.1178 0.486 Inf -0.242 0.9681
## Ext_Reserve - Reserve -0.1823 0.558 Inf -0.327 0.9428
##
## Saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.6931 0.707 Inf 0.980 0.5894
## (Bas-fond) - Reserve -0.9163 0.483 Inf -1.897 0.1395
## Ext_Reserve - Reserve -1.6094 0.632 Inf -2.545 0.0294
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emtpol4 <- lsmeans(glmpol2, ~ Saison)
## NOTE: Results may be misleading due to involvement in interactions
pairs(emtpol4)
## contrast estimate SE df z.ratio p.value
## Aout - Fevrier 0.0284 0.299 Inf 0.095 0.9950
## Aout - Juin 0.2594 0.322 Inf 0.805 0.7002
## Fevrier - Juin 0.2310 0.334 Inf 0.692 0.7681
##
## Results are averaged over the levels of: site
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
Filet - Abondance
glmpol3<-glmer(norga ~ site*Saison+(1|floraison), data = syntfpoll, family=poisson, nAGQ=2) #Estimation des paramètres du modèle par la Quadrature de Gauss-Hermite (Bolker, 2008)
summary(glmpol3)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: norga ~ site * Saison + (1 | floraison)
## Data: syntfpoll
##
## AIC BIC logLik deviance df.resid
## 109.8 127.4 -44.9 89.8 33
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.1105 -0.7552 -0.1464 0.7620 2.5113
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 0.09515 0.3085
## Number of obs: 43, groups: floraison, 17
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.2539 0.2702 4.641 3.47e-06 ***
## siteExt_Reserve 0.9613 0.2959 3.249 0.00116 **
## siteReserve 0.3861 0.3393 1.138 0.25509
## SaisonFevrier 1.1757 0.2962 3.969 7.22e-05 ***
## SaisonJuin -0.6605 0.4387 -1.506 0.13219
## siteExt_Reserve:SaisonFevrier -0.2265 0.3590 -0.631 0.52804
## siteReserve:SaisonFevrier 0.4349 0.3782 1.150 0.25022
## siteExt_Reserve:SaisonJuin -0.3703 0.5332 -0.695 0.48736
## siteReserve:SaisonJuin 0.7067 0.5225 1.353 0.17614
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv SsnFvr SasnJn sE_R:SF stR:SF sE_R:SJ
## sitExt_Rsrv -0.747
## siteReserve -0.743 0.578
## SaisonFevrr -0.806 0.653 0.669
## SaisonJuin -0.587 0.450 0.471 0.506
## stExt_Rs:SF 0.682 -0.806 -0.557 -0.816 -0.424
## stRsrv:SsnF 0.649 -0.517 -0.879 -0.778 -0.408 0.646
## stExt_Rs:SJ 0.423 -0.551 -0.316 -0.359 -0.787 0.445 0.270
## stRsrv:SsnJ 0.479 -0.374 -0.635 -0.420 -0.825 0.352 0.556 0.647
Anova(glmpol3, type=3, method="chisq") #methode chis2 car glmer et type 3 car plan déséquilibré et présence d'une interaction
## Analysis of Deviance Table (Type III Wald chisquare tests)
##
## Response: norga
## Chisq Df Pr(>Chisq)
## (Intercept) 21.5385 1 3.468e-06 ***
## site 11.3752 2 0.003388 **
## Saison 32.3448 2 9.471e-08 ***
## site:Saison 6.9914 4 0.136341
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Test des résidus
library(DHARMa)
plot(simulateResiduals(glmpol3))
library(MuMIn) #Détermination du r2
r.squaredGLMM(glmpol3) #R2m représente le r avec seulement les effets fixes, et r2c il y a les effets de groupes
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## R2m R2c
## delta 0.7828140 0.8886975
## lognormal 0.7869224 0.8933616
## trigamma 0.7783375 0.8836156
#trigamma la plus fiable
emtpol5<- lsmeans(glmpol3, ~ site, by="Saison")
pairs(emtpol5)
## Saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.9613 0.296 Inf -3.249 0.0033
## (Bas-fond) - Reserve -0.3861 0.339 Inf -1.138 0.4906
## Ext_Reserve - Reserve 0.5752 0.294 Inf 1.954 0.1237
##
## Saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.7348 0.213 Inf -3.457 0.0016
## (Bas-fond) - Reserve -0.8210 0.181 Inf -4.545 <.0001
## Ext_Reserve - Reserve -0.0862 0.194 Inf -0.444 0.8969
##
## Saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.5910 0.445 Inf -1.329 0.3792
## (Bas-fond) - Reserve -1.0928 0.404 Inf -2.707 0.0186
## Ext_Reserve - Reserve -0.5018 0.339 Inf -1.482 0.2996
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emtpol6 <- lsmeans(glmpol3, ~ Saison)
## NOTE: Results may be misleading due to involvement in interactions
pairs(emtpol6)
## contrast estimate SE df z.ratio p.value
## Aout - Fevrier -1.245 0.147 Inf -8.491 <.0001
## Aout - Juin 0.548 0.214 Inf 2.567 0.0277
## Fevrier - Juin 1.794 0.191 Inf 9.412 <.0001
##
## Results are averaged over the levels of: site
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
piege abondance
glmpol4<-glmer(norga ~ site*Saison+(1|floraison), data = syntppoll, family=poisson, nAGQ=2) #Estimation des paramètres du modèle par la Quadrature de Gauss-Hermite (Bolker, 2008)
summary(glmpol4)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: norga ~ site * Saison + (1 | floraison)
## Data: syntppoll
##
## AIC BIC logLik deviance df.resid
## 113.8 126.4 -46.9 93.8 16
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.5439 -0.7433 -0.1272 0.6862 4.2084
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 0.3722 0.6101
## Number of obs: 26, groups: floraison, 16
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.74839 0.44576 1.679 0.09317 .
## siteExt_Reserve 1.18251 0.66062 1.790 0.07345 .
## siteReserve 0.49530 0.62501 0.792 0.42809
## SaisonFevrier 0.45247 0.52054 0.869 0.38472
## SaisonJuin 0.12282 0.67303 0.182 0.85520
## siteExt_Reserve:SaisonFevrier 0.07825 0.86530 0.090 0.92794
## siteReserve:SaisonFevrier 0.61604 0.75119 0.820 0.41217
## siteExt_Reserve:SaisonJuin -2.03371 0.97788 -2.080 0.03755 *
## siteReserve:SaisonJuin 2.58270 0.83295 3.101 0.00193 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv SsnFvr SasnJn sE_R:SF stR:SF sE_R:SJ
## sitExt_Rsrv -0.674
## siteReserve -0.640 0.431
## SaisonFevrr -0.554 0.374 0.425
## SaisonJuin -0.657 0.443 0.416 0.360
## stExt_Rs:SF 0.605 -0.824 -0.421 -0.703 -0.393
## stRsrv:SsnF 0.473 -0.319 -0.774 -0.686 -0.310 0.541
## stExt_Rs:SJ 0.468 -0.684 -0.277 -0.262 -0.695 0.570 0.199
## stRsrv:SsnJ 0.486 -0.328 -0.693 -0.314 -0.775 0.315 0.535 0.599
Anova(glmpol4, type=3, method="chisq") #methode chis2 car glmer et type 3 car plan déséquilibré et présence d'une interaction
## Analysis of Deviance Table (Type III Wald chisquare tests)
##
## Response: norga
## Chisq Df Pr(>Chisq)
## (Intercept) 2.8188 1 0.09317 .
## site 3.2046 2 0.20143
## Saison 0.7752 2 0.67868
## site:Saison 53.3503 4 7.198e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Test des résidus
library(DHARMa)
plot(simulateResiduals(glmpol4))
library(MuMIn) #Détermination du r2
r.squaredGLMM(glmpol4) #R2m représente le r avec seulement les effets fixes, et r2c il y a les effets de groupes
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## R2m R2c
## delta 0.7329657 0.9460272
## lognormal 0.7347253 0.9482982
## trigamma 0.7310475 0.9435514
#trigamma la plus fiable
emtpol7<- lsmeans(glmpol4, ~ site, by="Saison")
pairs(emtpol7)
## Saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -1.183 0.661 Inf -1.790 0.1729
## (Bas-fond) - Reserve -0.495 0.625 Inf -0.792 0.7077
## Ext_Reserve - Reserve 0.687 0.686 Inf 1.002 0.5759
##
## Saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -1.261 0.493 Inf -2.558 0.0284
## (Bas-fond) - Reserve -1.111 0.478 Inf -2.325 0.0524
## Ext_Reserve - Reserve 0.149 0.428 Inf 0.349 0.9349
##
## Saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.851 0.713 Inf 1.193 0.4573
## (Bas-fond) - Reserve -3.078 0.602 Inf -5.110 <.0001
## Ext_Reserve - Reserve -3.929 0.489 Inf -8.029 <.0001
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emtpol8 <- lsmeans(glmpol4, ~ Saison)
## NOTE: Results may be misleading due to involvement in interactions
pairs(emtpol8)
## contrast estimate SE df z.ratio p.value
## Aout - Fevrier -0.684 0.324 Inf -2.109 0.0879
## Aout - Juin -0.306 0.388 Inf -0.789 0.7098
## Fevrier - Juin 0.378 0.418 Inf 0.904 0.6378
##
## Results are averaged over the levels of: site
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
#Réseaux bipartites
Août
## Loading required package: sna
## Loading required package: statnet.common
##
## Attaching package: 'statnet.common'
## The following objects are masked from 'package:base':
##
## attr, order
## Loading required package: network
##
## 'network' 1.18.1 (2023-01-24), part of the Statnet Project
## * 'news(package="network")' for changes since last version
## * 'citation("network")' for citation information
## * 'https://statnet.org' for help, support, and other information
## sna: Tools for Social Network Analysis
## Version 2.7-1 created on 2023-01-24.
## copyright (c) 2005, Carter T. Butts, University of California-Irvine
## For citation information, type citation("sna").
## Type help(package="sna") to get started.
##
## Attaching package: 'sna'
## The following objects are masked from 'package:ape':
##
## consensus, degree
## The following object is masked from 'package:nlme':
##
## gapply
## This is bipartite 2.18.
## For latest changes see versionlog in ?"bipartite-package". For citation see: citation("bipartite").
## Have a nice time plotting and analysing two-mode networks.
##
## Attaching package: 'bipartite'
## The following object is masked from 'package:MuMIn':
##
## nested
## The following object is masked from 'package:vegan':
##
## nullmodel
Aout - Réserve
plot1<-plotweb(rsar,method="cca",
text.rot=90,
col.high=
c(rep("#26A69A",1),rep("#CDDC39",1),rep("#FF5722",1),rep("#26A69A",1),rep("#CDDC39",2),
rep("#FF5722",2),rep("#CDDC39",2),rep("#26A69A",1)),
col.interaction="#263238",
high.spacing =0.001,
low.spacing =0.01,
col.low="#FAFAFA",
bor.col.high="white",
bor.col.low="black",
high.lablength=9,
bor.col.interaction = "white", #remove the black border color
high.lab.dis = 0,
adj.high=-0.1,
low.xoff = 0,
ybig=0,
y.lim = c(0,2))
Indices
null.t.test(rsar, index=c("connectance","interaction evenness","modularity"))
## obs null mean lower CI upper CI t
## connectance 0.3454545 0.3872727 0.3776465 0.3968989 8.884913
## modularity Q 0.4334705 0.3774120 0.3611314 0.3936926 -7.042288
## interaction evenness 0.7102788 0.7436814 0.7362179 0.7511450 9.153285
## P
## connectance 8.983701e-10
## modularity Q 9.566584e-08
## interaction evenness 4.721408e-10
# Tous significativement différents
Modèle nul + Comparaison des connectances
library(vegan)
library(bipartite)
obs1 <- unlist (networklevel (rsar, index="connectance"))
obs0d <- unlist (networklevel (rsar, index="H2"))
obs0e<-nestednodf(rsar)
#Avoir la connectance du réseau -> faire pour 3 saisons et avoir une moyenne et une variabilité pour faire une figure?
nul0<-nullmodel(rsar,method="r2dtable")
null0d<-unlist(sapply(nul0,networklevel,index="H2"))
null0e<-unlist(sapply(nul0,nestednodf))
#Valeurs du paramètres sous un modèle nul
Aout - Extérieur
plot2<-plotweb(rsae,method="cca",
text.rot=90,
col.high=
c(rep("#26A69A",2), rep("#CDDC39",1), rep("#26A69A",1),rep("#CDDC39",3), rep("#26A69A",1), rep("#CDDC39",1),
rep("#26A69A",1), rep("#CDDC39",2),rep("#FF5722",1),rep("#26A69A",5)),
col.interaction="#263238",
high.spacing =0.001,
low.spacing =0.01,
col.low="#FAFAFA",
bor.col.high="white",
bor.col.low="black",
high.lablength=9,
bor.col.interaction = "white", #remove the black border color
high.lab.dis = 0,
adj.high=-0.1,
low.xoff = 0,
ybig=0,
y.lim = c(0,2))
Indices
networklevel(rsae)
## connectance web asymmetry
## 0.36666667 0.56521739
## links per species number of compartments
## 1.43478261 1.00000000
## compartment diversity cluster coefficient
## NA 0.30000000
## modularity Q nestedness
## 0.30473373 18.38844379
## NODF weighted nestedness
## 57.62781186 0.61746997
## weighted NODF interaction strength asymmetry
## 25.59986367 0.05263492
## specialisation asymmetry linkage density
## -0.29134359 5.38058336
## weighted connectance Fisher alpha
## 0.23393841 38.83866585
## Shannon diversity interaction evenness
## 3.33321599 0.74074599
## Alatalo interaction evenness H2
## 0.82544279 0.22026748
## number.of.species.HL number.of.species.LL
## 18.00000000 5.00000000
## mean.number.of.shared.partners.HL mean.number.of.shared.partners.LL
## 0.93464052 2.30000000
## cluster.coefficient.HL cluster.coefficient.LL
## 0.54230769 0.53739316
## weighted.cluster.coefficient.HL weighted.cluster.coefficient.LL
## 0.70488722 0.22080985
## niche.overlap.HL niche.overlap.LL
## 0.48813593 0.38197616
## togetherness.HL togetherness.LL
## 0.31699346 0.13580247
## C.score.HL C.score.LL
## 0.28976035 0.30964286
## V.ratio.HL V.ratio.LL
## 1.21090909 5.88372093
## discrepancy.HL discrepancy.LL
## 9.00000000 8.00000000
## extinction.slope.HL extinction.slope.LL
## 5.29461804 1.57002101
## robustness.HL robustness.LL
## 0.75936285 0.42184878
## functional.complementarity.HL functional.complementarity.LL
## 26.76886424 24.42534585
## partner.diversity.HL partner.diversity.LL
## 0.81844807 1.99818433
## generality.HL vulnerability.LL
## 2.46854646 8.29262026
null.t.test(rsae, index=c("connectance","interaction evenness","H2","modularity"))
## obs null mean lower CI upper CI t
## connectance 0.3666667 0.3551852 0.3488804 0.3614900 -3.724524
## modularity Q 0.3047337 0.3204635 0.3107326 0.3301944 3.306067
## interaction evenness 0.7407460 0.7317846 0.7275702 0.7359990 -4.348903
## H2 0.2202675 0.2586846 0.2406176 0.2767517 4.348903
## P
## connectance 0.0008405781
## modularity Q 0.0025270212
## interaction evenness 0.0001540346
## H2 0.0001540346
# Tous significativement différents
Modèle nul + Comparaison des connectances
library(vegan)
obs2 <- unlist (networklevel (rsae, index="connectance"))
obs2d <- unlist (networklevel (rsae, index="H2"))
obs2e<-nestednodf(rsae)
#Avoir la connectance du réseau -> faire pour 3 saisons et avoir une moyenne et une variabilité pour faire une figure?
nul2<-nullmodel(rsae,method="r2dtable")
null2d<-unlist(sapply(nul2,networklevel,index="H2"))
#Valeurs du paramètres sous un modèle nul
Aout - Bas-Fond
plot3<-plotweb(rsab,method="cca",
text.rot=90,
col.high=
c(rep("#CDDC39",3),rep("#26A69A",1),rep("#CDDC39",1),rep("#FF5722",1), rep("#CDDC39",1),rep("#26A69A",4),rep("purple",1)),
col.interaction="#263238",
high.spacing =0.001,
low.spacing =0.01,
col.low="#FAFAFA",
bor.col.high="white",
bor.col.low="black",
high.lablength=9,
bor.col.interaction = "white", #remove the black border color
high.lab.dis = 0,
adj.high=-0.1,
low.xoff = 0,
ybig=0,
y.lim = c(0,2))
Indices
null.t.test(rsab, index=c("connectance","interaction evenness","H2","modularity"))
## obs null mean lower CI upper CI t
## connectance 0.2909091 0.3042424 0.2969056 0.3115792 3.716848
## modularity Q 0.5370370 0.4989712 0.4800500 0.5178924 -4.114616
## interaction evenness 0.6828329 0.6964432 0.6883646 0.7045217 3.445652
## H2 0.2579019 0.1665826 0.1123784 0.2207868 -3.445652
## P
## connectance 0.0008579960
## modularity Q 0.0002928185
## interaction evenness 0.0017579587
## H2 0.0017579587
# Tous significativement différents
Modèle nul + Comparaison des connectances
library(vegan)
obs3 <- unlist (networklevel (rsab, index="connectance"))
obs3d <- unlist (networklevel (rsab, index="H2"))
obs3e<-nestednodf(rsab)
#Avoir la connectance du réseau -> faire pour 3 saisons et avoir une moyenne et une variabilité pour faire une figure?
nul3<-nullmodel(rsab,method="r2dtable")
null3d<-unlist(sapply(nul3,networklevel,index="H2"))
#Valeurs du paramètres sous un modèle nul
Février
Février - Réserve
Indices
null.t.test(rsfr, index=c("connectance","interaction evenness","modularity"))
## obs null mean lower CI upper CI t
## connectance 0.4625000 0.4966667 0.4900733 0.5032600 10.59834
## modularity Q 0.2225677 0.1634443 0.1574836 0.1694051 -20.28618
## interaction evenness 0.7061244 0.7361216 0.7340904 0.7381527 30.20498
## P
## connectance 1.737482e-11
## modularity Q 1.116720e-18
## interaction evenness 1.814629e-23
# Tous significativement différents
Modèle nul + Comparaison des connectances
library(vegan)
obs4 <- unlist (networklevel (rsfr, index="connectance"))
obs4d <- unlist (networklevel (rsfr, index="H2"))
obs4e<-nestednodf(rsfr)
#Avoir la connectance du réseau -> faire pour 3 saisons et avoir une moyenne et une variabilité pour faire une figure?
nul4<-nullmodel(rsfr,method="r2dtable")
null4d<-unlist(sapply(nul4,networklevel,index="H2"))
#Valeurs du paramètres sous un modèle nul
Février - Ext_Parcelle
Indices
null.t.test(rsfe, index=c("connectance","interaction evenness","H2","modularity"))
## obs null mean lower CI upper CI t
## connectance 0.5185185 0.6345679 0.6206272 0.6485086 17.02553
## modularity Q 0.2062186 0.1168775 0.1096739 0.1240812 -25.36536
## interaction evenness 0.6047793 0.6404521 0.6380971 0.6428070 30.98139
## H2 0.3250773 0.1257983 0.1126429 0.1389536 -30.98139
## P
## connectance 1.226617e-16
## modularity Q 2.399365e-21
## interaction evenness 8.880611e-24
## H2 8.880611e-24
Modèle nul + Comparaison des connectances
library(vegan)
obs5 <- unlist (networklevel (rsfe, index="connectance"))
obs5d <- unlist (networklevel (rsfe, index="H2"))
obs5e<-nestednodf(rsfe)
#Avoir la connectance du réseau -> faire pour 3 saisons et avoir une moyenne et une variabilité pour faire une figure?
nul5<-nullmodel(rsfe, method="r2dtable")
null5d<-unlist(sapply(nul5,networklevel,index="H2"))
#Valeurs du paramètres sous un modèle nul
Février - Bas_Fond
Indices
null.t.test(rsfb, index=c("connectance","interaction evenness","modularity"))
## obs null mean lower CI upper CI t
## connectance 0.3125000 0.3241667 0.3167173 0.3316160 3.203112
## modularity Q 0.3158284 0.2739275 0.2631068 0.2847482 -7.919739
## interaction evenness 0.6386581 0.6531544 0.6485982 0.6577107 6.507176
## P
## connectance 3.292161e-03
## modularity Q 9.820748e-09
## interaction evenness 4.002054e-07
Modèle nul + Comparaison des connectances
library(vegan)
obs6 <- unlist (networklevel (rsfb, index="connectance"))
obs6d <- unlist (networklevel (rsfb, index="H2"))
obs6e<-nestednodf(rsfb)
#Avoir la connectance du réseau -> faire pour 3 saisons et avoir une moyenne et une variabilité pour faire une figure?
nul6<-nullmodel(rsfb, method="r2dtable")
null6d<-unlist(sapply(nul6,networklevel,index="H2"))
#Valeurs du paramètres sous un modèle nul
Juin
Juin- Réserve
Indices
null.t.test(rsjr, index=c("connectance","interaction evenness","modularity"))
## obs null mean lower CI upper CI t
## connectance 0.4285714 0.5123810 0.5023050 0.5224569 17.01182
## modularity Q 0.3954082 0.2906463 0.2774490 0.3038435 -16.23541
## interaction evenness 0.7265097 0.7785794 0.7723046 0.7848541 16.97183
## P
## connectance 1.253033e-16
## modularity Q 4.287229e-16
## interaction evenness 1.333483e-16
# Tous significativement différents
Modèle nul + Comparaison des connectances
library(vegan)
obs7 <- unlist (networklevel (rsjr, index="connectance"))
obs7d <- unlist (networklevel (rsjr, index="H2"))
obs7e<-nestednodf(rsjr)
#Avoir la connectance du réseau -> faire pour 3 saisons et avoir une moyenne et une variabilité pour faire une figure?
nul7<-nullmodel(rsjr,N=500, method="r2dtable")
null7d<-unlist(sapply(nul7,networklevel,index="H2"))
#Valeurs du paramètres sous un modèle nul
Juin - Ext_Parcelle
plotweb(rsje,method="cca",
text.rot=90,
col.high=
c(rep("#26A69A",1),rep("#CDDC39",2),rep("#26A69A",2)),
col.interaction="#263238",
high.spacing =0.001,
low.spacing =0.01,
col.low="#FAFAFA",
bor.col.high="white",
bor.col.low="black",
high.lablength=9,
bor.col.interaction = "white", #remove the black border color
high.lab.dis = 0,
adj.high=-0.1,
low.xoff = 0,
ybig=0,
y.lim = c(0,2))
null.t.test(rsje, index=c("connectance","interaction evenness","H2"))
## obs null mean lower CI upper CI t
## connectance 0.4666667 0.6044444 0.5860310 0.6228578 15.30337
## interaction evenness 0.6134756 0.7504326 0.7390070 0.7618582 24.51586
## H2 0.8449203 0.1836193 0.1295844 0.2376542 -25.03033
## P
## connectance 2.001776e-15
## interaction evenness 6.174708e-21
## H2 3.471158e-21
Modèle nul + Comparaison des connectances
library(vegan)
obs8 <- unlist (networklevel (rsje, index="connectance"))
obs8d <- unlist (networklevel (rsje, index="H2"))
obs8e<-nestednodf(rsje)
#Avoir la connectance du réseau -> faire pour 3 saisons et avoir une moyenne et une variabilité pour faire une figure?
nul8<-nullmodel(rsje,N=500, method="r2dtable")
null8d<-unlist(sapply(nul8,networklevel,index="H2"))
#Valeurs du paramètres sous un modèle nul
Juin - Bas_Fond
Indices
## obs null mean lower CI upper CI t
## connectance 0.2800000 0.3360000 0.32384673 0.3481533 9.424038
## modularity Q 0.6172840 0.4707819 0.44358349 0.4979803 -11.016468
## interaction evenness 0.5869003 0.6538944 0.63935518 0.6684337 9.424038
## H2 0.5921638 0.1776491 0.08769008 0.2676082 -9.424038
## P
## connectance 2.491065e-10
## modularity Q 7.022318e-12
## interaction evenness 2.491065e-10
## H2 2.491065e-10
Modèle nul + Comparaison des connectances
Connectance & Création du tableau
Graph - Connectance
## Warning in geom_point(shape = 18, size = 3, alpha = 0.5, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
Modularité
modulobsr<-c(0.4234,0.4492,0.4619)
modulobsrobse<-c(0.3406,0.3629,0.4870)
modulobsrobsb<-c(0.3382,0.3629,0.4633)
modulr0<-c(0.3624,0.3784,0.3667)
module0<-c(0.2781,0.2737,0.3852)
modulb0<-c(0.2763,0.2737,0.3361)
modularity<-c(modulobsr,modulobsrobse,modulobsrobsb,modulr0,module0,modulb0)
parars$modularity<-modularity
Graph - Modularity
## Warning in geom_point(shape = 18, size = 3, alpha = 0.5, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
Interacton.evennes
evenobsr<-c(0.7488,0.7482,0.7229)
evenobsrobse<-c(0.7319,0.6665,0.7653)
evenobsrobsb<-c(0.7322,0.6665,0.6909)
evenr0<-c(0.7709,0.7765,0.7613)
evene0<-c(0.7551,0.6913,0.7936)
evenb0<-c(0.755,0.6916,0.7439)
evenness<-c(evenobsr,evenobsrobse,evenobsrobsb,evenr0,evene0,evenb0)
parars$evenness<-evenness
Graph - Evenness
## Warning in geom_point(shape = 18, size = 3, alpha = 0.5, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
H2
h2obsr<-c(0.3053,0.3744,0.4139)
h2obse<-c(0.2393,0.2771,0.3416)
h2obsb<-c(0.2393,0.2771,0.3859)
h2r0<-c(0.1873,0.2155,0.1915)
h2e0<-c(0.1269,0.1116,0.1676)
h2b0<-c(0.1234,0.1085,0.1344)
H2<-c(h2obsr,h2obse,h2obsb,h2r0,h2e0,h2b0)
parars$H2<-H2
Graph - H2 à modifier
## Warning in geom_point(shape = 18, size = 3, alpha = 0.5, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
Nestedness
obs9e
## N columns : 0.04140787
## N rows : 20
## NODF : 0.1237113
## Matrix fill: 0.02
nestobsr<-c(0.4687,0.5706,0.5520)
nestobse<-c(1.05,0.29,1.41)
nestobsb<-c(0.3538,0.3871,0.1566)
nestr0<-c(0,0,0)
neste0<-c(0,0,0)
nestb0<-c(0,0,0)
nestedness<-c(nestobsr,nestobse,nestobsb,nestr0,neste0,nestb0)
parars$nestedness<-nestedness
Graph - H2 à modifier
## Warning in geom_point(shape = 18, size = 3, alpha = 0.5, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
par(mfrow = c(2,2))
nc
nv
nx
nw
#Annexe : Figures Ordre Filet Hymenoptera
library(ggplot2)
coloror <- c("#333333","#FB8C00","#26A69A")
syntfilethy<-subset(syntfilet,syntfilet$ordre=="Hymenoptera")
ggplot(syntfilethy, aes(x=Saison, y=rspe,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.3),aes(ymin=rspe-sd(rspe), ymax=rspe+sd(rspe)))+
theme_bw() + scale_color_manual(values=coloror) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.3)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +
coord_cartesian(ylim = c(0, 25))+
ggtitle("Filet - Richesse spécifique") +
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
Coleoptera
colorco<- c("#333333","#FB8C00","#D32F2F")
syntfiletco<-subset(syntfilet,syntfilet$ordre=="Coleoptera")
ggplot(syntfiletco, aes(x=Saison, y=rspe,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.3),aes(ymin=rspe-sd(rspe), ymax=rspe+sd(rspe)))+
theme_bw() + scale_color_manual(values=colorco) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.3)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +
coord_cartesian(ylim = c(0, 10))+
ggtitle("Filet - Richesse spécifique") +
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
Diptera
syntfiletdi<-subset(syntfilet,syntfilet$ordre=="Diptera")
colordi<- c("#333333","#FB8C00","#CDDC39")
ggplot(syntfiletdi, aes(x=Saison, y=rspe,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.3),aes(ymin=rspe-sd(rspe), ymax=rspe+sd(rspe)))+
theme_bw() + scale_color_manual(values=colordi) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.3)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +
coord_cartesian(ylim = c(0, 10))+
ggtitle("Filet - Richesse spécifique") +
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
Autres
syntfiletau<-subset(syntfilet,syntfilet$ordre=="Autres")
colorau<- c("#333333","#FB8C00","purple")
ggplot(syntfiletau, aes(x=Saison, y=rspe,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.3),aes(ymin=rspe-sd(rspe), ymax=rspe+sd(rspe)))+
theme_bw() + scale_color_manual(values=colorau) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.3)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +
coord_cartesian(ylim = c(0, 10))+
ggtitle("Filet - Richesse spécifique") +
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
Pieges
Hymenoptera
library(ggplot2)
coloror <- c("#333333","#FB8C00","#26A69A")
syntpiegehy<-subset(syntpiege,syntpiege$ordre=="Hymenoptera")
ggplot(syntpiegehy, aes(x=Saison, y=rspe,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.3),aes(ymin=rspe-sd(rspe), ymax=rspe+sd(rspe)))+
theme_bw() + scale_color_manual(values=coloror) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.3)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +
coord_cartesian(ylim = c(0, 25))+
ggtitle("Piege - Richesse spécifique") +
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
Coleoptera
colorco<- c("#333333","#FB8C00","#D32F2F")
syntpiegeco<-subset(syntpiege,syntpiege$ordre=="Coleoptera")
ggplot(syntpiegeco, aes(x=Saison, y=rspe,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.3),aes(ymin=rspe-sd(rspe), ymax=rspe+sd(rspe)))+
theme_bw() + scale_color_manual(values=colorco) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.3)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +
coord_cartesian(ylim = c(0, 8))+
ggtitle("Piege - Richesse spécifique") +
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
Diptera
syntpiegedi<-subset(syntpiege,syntpiege$ordre=="Diptera")
colordi<- c("#333333","#FB8C00","#CDDC39")
ggplot(syntpiegedi, aes(x=Saison, y=rspe,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.3),aes(ymin=rspe-sd(rspe), ymax=rspe+sd(rspe)))+
theme_bw() + scale_color_manual(values=colordi) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.3)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +
coord_cartesian(ylim = c(0, 20))+
ggtitle("Piege - Richesse spécifique") +
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
Autres
syntpiegeau<-subset(syntpiege,syntpiege$ordre=="Autres")
colorau<- c("#333333","#FB8C00","purple")
ggplot(syntpiegeau, aes(x=Saison, y=rspe,facet=site, color=site)) +
geom_point(shape=18,size=3, alpha=0.25, position=position_dodge(width=0.3),aes(ymin=rspe-sd(rspe), ymax=rspe+sd(rspe)))+
theme_bw() + scale_color_manual(values=colorau) +stat_summary(fun.data=mean_sdl, fun.args = list(mult = 1), geom="pointrange", shape=19, size=1,alpha=1,position=position_dodge(width=0.3)) + labs(x = "Saison", y = "Richesse spécifique", fill="Site") +
coord_cartesian(ylim = c(0, 15))+
ggtitle("Filet - Richesse spécifique") +
theme(axis.text.y = element_text(face="bold",colour = "black", size = 13),
axis.text.x = element_text(face="bold",colour = "black", size = 13),
legend.text = element_text(size = 13, colour ="black"))
## Warning in geom_point(shape = 18, size = 3, alpha = 0.25, position =
## position_dodge(width = 0.3), : Ignoring unknown aesthetics: ymin and ymax
#Annexe : Modèles Ordre
Hymenoptera - Richesse filet & piege
glmhy1 <- glmer(rspe ~ site*saison+(1|floraison ), data = syntfilethy, family = poisson, nAGQ=2)
## boundary (singular) fit: see help('isSingular')
summary(glmhy1)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * saison + (1 | floraison)
## Data: syntfilethy
##
## AIC BIC logLik deviance df.resid
## 55.1 72.7 -17.6 35.1 33
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.9379 -0.4867 0.0000 0.3795 2.4463
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 0 0
## Number of obs: 43, groups: floraison, 17
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.7918 0.1826 9.814 < 2e-16 ***
## siteExt_Reserve 0.1823 0.2472 0.738 0.46080
## siteReserve -0.1431 0.2679 -0.534 0.59330
## saisonFevrier 1.2809 0.2064 6.207 5.41e-10 ***
## saisonJuin -0.2231 0.2739 -0.815 0.41518
## siteExt_Reserve:saisonFevrier -0.8571 0.3173 -2.701 0.00691 **
## siteReserve:saisonFevrier -0.1952 0.3067 -0.637 0.52438
## siteExt_Reserve:saisonJuin 0.3032 0.3584 0.846 0.39753
## siteReserve:saisonJuin 0.3662 0.3831 0.956 0.33912
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv ssnFvr sasnJn sE_R:F stRs:F sE_R:J
## sitExt_Rsrv -0.739
## siteReserve -0.681 0.503
## saisonFevrr -0.885 0.653 0.603
## saisonJuin -0.667 0.492 0.454 0.590
## stExt_Rsr:F 0.575 -0.779 -0.392 -0.650 -0.384
## stRsrv:ssnF 0.595 -0.440 -0.874 -0.673 -0.397 0.438
## stExt_Rsr:J 0.509 -0.690 -0.347 -0.451 -0.764 0.537 0.303
## stRsrv:ssnJ 0.477 -0.352 -0.699 -0.422 -0.715 0.274 0.611 0.546
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')
anova(glmhy1)
## Analysis of Variance Table
## npar Sum Sq Mean Sq F value
## site 2 16.040 8.020 8.0201
## saison 2 91.028 45.514 45.5142
## site:saison 4 14.968 3.742 3.7419
#Test des résidus
library(DHARMa)
plot(simulateResiduals(glmhy1))
library(MuMIn) #Détermination du r2
r.squaredGLMM(glmhy1) #R2m représente le r avec seulement les effets fixes, et r2c il y a les effets de groupes
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## R2m R2c
## delta 0.6903345 0.6903345
## lognormal 0.7016562 0.7016562
## trigamma 0.6781456 0.6781456
#trigamma la plus fiable
glmhy2 <- glmer(rspe ~ site*saison+(1|floraison), data = syntpiegehy, family = poisson, nAGQ=2)
## boundary (singular) fit: see help('isSingular')
summary(glmhy2)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * saison + (1 | floraison)
## Data: syntpiegehy
##
## AIC BIC logLik deviance df.resid
## 43.1 55.7 -11.5 23.1 16
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.6002 -0.7091 0.0000 0.4818 2.8311
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 0 0
## Number of obs: 26, groups: floraison, 16
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.098612 0.333333 3.296 0.000981 ***
## siteExt_Reserve 0.893818 0.395684 2.259 0.023888 *
## siteReserve 0.747214 0.404651 1.847 0.064810 .
## saisonFevrier 0.575364 0.416667 1.381 0.167318
## saisonJuin 0.105361 0.459468 0.229 0.818628
## siteExt_Reserve:saisonFevrier -1.063717 0.574610 -1.851 0.064141 .
## siteReserve:saisonFevrier -1.440362 0.592657 -2.430 0.015084 *
## siteExt_Reserve:saisonJuin -0.200671 0.553684 -0.362 0.717032
## siteReserve:saisonJuin -0.005277 0.557998 -0.009 0.992454
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv ssnFvr sasnJn sE_R:F stRs:F sE_R:J
## sitExt_Rsrv -0.842
## siteReserve -0.824 0.694
## saisonFevrr -0.800 0.674 0.659
## saisonJuin -0.725 0.611 0.598 0.580
## stExt_Rsr:F 0.580 -0.689 -0.478 -0.725 -0.421
## stRsrv:ssnF 0.562 -0.474 -0.683 -0.703 -0.408 0.510
## stExt_Rsr:J 0.602 -0.715 -0.496 -0.482 -0.830 0.492 0.339
## stRsrv:ssnJ 0.597 -0.503 -0.725 -0.478 -0.823 0.347 0.495 0.683
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')
anova(glmhy2)
## Analysis of Variance Table
## npar Sum Sq Mean Sq F value
## site 2 4.8794 2.43972 2.4397
## saison 2 1.0546 0.52729 0.5273
## site:saison 4 8.6078 2.15194 2.1519
plot(simulateResiduals(glmhy2))
r.squaredGLMM(glmhy2)
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## R2m R2c
## delta 0.4332043 0.4332043
## lognormal 0.4551452 0.4551452
## trigamma 0.4095678 0.4095678
library(emmeans)
emhy1 <- lsmeans(glmhy1, ~ site, by="saison")
pairs(emhy1)
## saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.182 0.247 Inf -0.738 0.7412
## (Bas-fond) - Reserve 0.143 0.268 Inf 0.534 0.8546
## Ext_Reserve - Reserve 0.325 0.257 Inf 1.264 0.4154
##
## saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.675 0.199 Inf 3.393 0.0020
## (Bas-fond) - Reserve 0.338 0.149 Inf 2.268 0.0603
## Ext_Reserve - Reserve -0.336 0.208 Inf -1.617 0.2383
##
## saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.486 0.259 Inf -1.871 0.1470
## (Bas-fond) - Reserve -0.223 0.274 Inf -0.815 0.6938
## Ext_Reserve - Reserve 0.262 0.243 Inf 1.080 0.5263
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emhy2 <- lsmeans(glmhy2, ~ site, by="saison")
pairs(emhy2)
## saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.8938 0.396 Inf -2.259 0.0617
## (Bas-fond) - Reserve -0.7472 0.405 Inf -1.847 0.1546
## Ext_Reserve - Reserve 0.1466 0.313 Inf 0.468 0.8863
##
## saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.1699 0.417 Inf 0.408 0.9124
## (Bas-fond) - Reserve 0.6931 0.433 Inf 1.601 0.2453
## Ext_Reserve - Reserve 0.5232 0.486 Inf 1.077 0.5285
##
## saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.6931 0.387 Inf -1.790 0.1730
## (Bas-fond) - Reserve -0.7419 0.384 Inf -1.931 0.1300
## Ext_Reserve - Reserve -0.0488 0.312 Inf -0.156 0.9866
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
Diptera - Richesse filet & piege
glmdi1<-glmer(rspe ~ site*saison+(1|floraison), data = syntfiletdi, family = poisson, nAGQ=2)
## boundary (singular) fit: see help('isSingular')
glmdi2<-glmer(rspe ~ site*saison+(1|floraison), data = syntpiegedi, family = poisson, nAGQ=2)
## boundary (singular) fit: see help('isSingular')
summary(glmdi1)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * saison + (1 | floraison)
## Data: syntfiletdi
##
## AIC BIC logLik deviance df.resid
## 52.1 69.7 -16.0 32.1 33
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.34164 -0.52994 -0.09759 0.54998 2.00000
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 7.541e-16 2.746e-08
## Number of obs: 43, groups: floraison, 17
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.52606 0.20851 7.319 2.5e-13 ***
## siteExt_Reserve 0.04256 0.29180 0.146 0.88404
## siteReserve -0.09097 0.30182 -0.301 0.76310
## saisonFevrier -0.57054 0.34699 -1.644 0.10012
## saisonJuin -1.52606 0.49344 -3.093 0.00198 **
## siteExt_Reserve:saisonFevrier 0.73653 0.46999 1.567 0.11709
## siteReserve:saisonFevrier 0.74490 0.45609 1.633 0.10242
## siteExt_Reserve:saisonJuin 0.42744 0.64043 0.667 0.50449
## siteReserve:saisonJuin 1.04648 0.60665 1.725 0.08452 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv ssnFvr sasnJn sE_R:F stRs:F sE_R:J
## sitExt_Rsrv -0.715
## siteReserve -0.691 0.494
## saisonFevrr -0.601 0.429 0.415
## saisonJuin -0.423 0.302 0.292 0.254
## stExt_Rsr:F 0.444 -0.621 -0.306 -0.738 -0.187
## stRsrv:ssnF 0.457 -0.327 -0.662 -0.761 -0.193 0.562
## stExt_Rsr:J 0.326 -0.456 -0.225 -0.196 -0.770 0.283 0.149
## stRsrv:ssnJ 0.344 -0.246 -0.498 -0.207 -0.813 0.152 0.329 0.627
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')
anova(glmdi1)
## Analysis of Variance Table
## npar Sum Sq Mean Sq F value
## site 2 2.1220 1.0610 1.0610
## saison 2 17.8833 8.9416 8.9416
## site:saison 4 5.5578 1.3894 1.3894
r.squaredGLMM(glmdi1)
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## R2m R2c
## delta 0.5194504 0.5194504
## lognormal 0.5520962 0.5520962
## trigamma 0.4822161 0.4822161
summary(glmdi2)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * saison + (1 | floraison)
## Data: syntpiegedi
##
## AIC BIC logLik deviance df.resid
## 40.4 53.0 -10.2 20.4 16
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.51186 -0.59660 -0.06155 0.60593 1.88982
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 0 0
## Number of obs: 26, groups: floraison, 16
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.159e+00 1.961e-01 11.011 <2e-16 ***
## siteExt_Reserve 4.721e-16 2.774e-01 0.000 1.0000
## siteReserve 2.384e-01 2.622e-01 0.909 0.3633
## saisonFevrier -1.671e-01 2.897e-01 -0.577 0.5642
## saisonJuin -9.555e-01 3.721e-01 -2.568 0.0102 *
## siteExt_Reserve:saisonFevrier -6.061e-01 4.974e-01 -1.219 0.2230
## siteReserve:saisonFevrier -2.849e-01 4.023e-01 -0.708 0.4788
## siteExt_Reserve:saisonJuin -1.054e-01 5.367e-01 -0.196 0.8444
## siteReserve:saisonJuin -1.431e-01 5.096e-01 -0.281 0.7788
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv ssnFvr sasnJn sE_R:F stRs:F sE_R:J
## sitExt_Rsrv -0.707
## siteReserve -0.748 0.529
## saisonFevrr -0.677 0.479 0.506
## saisonJuin -0.527 0.373 0.394 0.357
## stExt_Rsr:F 0.394 -0.558 -0.295 -0.582 -0.208
## stRsrv:ssnF 0.487 -0.345 -0.652 -0.720 -0.257 0.419
## stExt_Rsr:J 0.365 -0.517 -0.273 -0.247 -0.693 0.288 0.178
## stRsrv:ssnJ 0.385 -0.272 -0.515 -0.261 -0.730 0.152 0.335 0.506
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')
anova(glmdi2)
## Analysis of Variance Table
## npar Sum Sq Mean Sq F value
## site 2 1.9455 0.9728 0.9728
## saison 2 24.7029 12.3514 12.3514
## site:saison 4 1.5824 0.3956 0.3956
r.squaredGLMM(glmdi2)
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## R2m R2c
## delta 0.5770711 0.5770711
## lognormal 0.5957295 0.5957295
## trigamma 0.5567002 0.5567002
plot(simulateResiduals(glmdi1))
plot(simulateResiduals(glmdi2))
emdi1 <- lsmeans(glmdi1, ~ site, by="saison")
pairs(emdi1)
## saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.0426 0.292 Inf -0.146 0.9883
## (Bas-fond) - Reserve 0.0910 0.302 Inf 0.301 0.9512
## Ext_Reserve - Reserve 0.1335 0.299 Inf 0.447 0.8958
##
## saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.7791 0.368 Inf -2.115 0.0869
## (Bas-fond) - Reserve -0.6539 0.342 Inf -1.912 0.1351
## Ext_Reserve - Reserve 0.1252 0.314 Inf 0.398 0.9163
##
## saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.4700 0.570 Inf -0.824 0.6878
## (Bas-fond) - Reserve -0.9555 0.526 Inf -1.816 0.1644
## Ext_Reserve - Reserve -0.4855 0.449 Inf -1.080 0.5262
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emdi2 <- lsmeans(glmdi2, ~ site, by="saison")
pairs(emdi2)
## saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.0000 0.277 Inf 0.000 1.0000
## (Bas-fond) - Reserve -0.2384 0.262 Inf -0.909 0.6345
## Ext_Reserve - Reserve -0.2384 0.262 Inf -0.909 0.6345
##
## saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.6061 0.413 Inf 1.468 0.3063
## (Bas-fond) - Reserve 0.0465 0.305 Inf 0.152 0.9873
## Ext_Reserve - Reserve -0.5596 0.415 Inf -1.347 0.3692
##
## saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.1054 0.459 Inf 0.229 0.9714
## (Bas-fond) - Reserve -0.0953 0.437 Inf -0.218 0.9741
## Ext_Reserve - Reserve -0.2007 0.449 Inf -0.446 0.8960
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
Coleoptera - Richesse filet & piege
glmco1<-glmer(rspe ~ site*saison+(1|floraison), data = syntfiletco, family = poisson, nAGQ=2)
## boundary (singular) fit: see help('isSingular')
glmco2<-glmer(rspe ~ site*saison+(1|floraison), data = syntpiegeco, family = poisson, nAGQ=2)
## boundary (singular) fit: see help('isSingular')
summary(glmco1)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * saison + (1 | floraison)
## Data: syntfiletco
##
## AIC BIC logLik deviance df.resid
## 41.7 59.3 -10.9 21.7 33
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.3416 -0.4743 0.0000 0.3162 1.6330
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 0 0
## Number of obs: 43, groups: floraison, 17
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 6.931e-01 3.162e-01 2.192 0.0284 *
## siteExt_Reserve -5.108e-01 5.164e-01 -0.989 0.3226
## siteReserve 4.700e-01 4.031e-01 1.166 0.2436
## saisonFevrier -2.256e-15 4.472e-01 0.000 1.0000
## saisonJuin -2.231e-01 4.743e-01 -0.470 0.6380
## siteExt_Reserve:saisonFevrier -5.878e-01 9.309e-01 -0.631 0.5278
## siteReserve:saisonFevrier -1.163e+00 6.801e-01 -1.710 0.0872 .
## siteExt_Reserve:saisonJuin 6.286e-01 7.091e-01 0.887 0.3753
## siteReserve:saisonJuin 3.409e-01 5.857e-01 0.582 0.5605
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv ssnFvr sasnJn sE_R:F stRs:F sE_R:J
## sitExt_Rsrv -0.612
## siteReserve -0.784 0.480
## saisonFevrr -0.707 0.433 0.555
## saisonJuin -0.667 0.408 0.523 0.471
## stExt_Rsr:F 0.340 -0.555 -0.266 -0.480 -0.226
## stRsrv:ssnF 0.465 -0.285 -0.593 -0.658 -0.310 0.316
## stExt_Rsr:J 0.446 -0.728 -0.350 -0.315 -0.669 0.404 0.207
## stRsrv:ssnJ 0.540 -0.331 -0.688 -0.382 -0.810 0.183 0.408 0.542
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')
anova(glmco1)
## Analysis of Variance Table
## npar Sum Sq Mean Sq F value
## site 2 7.3494 3.6747 3.6747
## saison 2 3.2362 1.6181 1.6181
## site:saison 4 5.5231 1.3808 1.3808
r.squaredGLMM(glmco1)
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## boundary (singular) fit: see help('isSingular')
## R2m R2c
## delta 0.3112688 0.3112688
## lognormal 0.3588407 0.3588407
## trigamma 0.2583123 0.2583123
summary(glmco2)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * saison + (1 | floraison)
## Data: syntpiegeco
##
## AIC BIC logLik deviance df.resid
## 37.2 49.8 -8.6 17.2 16
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.2910 -0.5774 0.0000 0.5774 1.1547
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 0 0
## Number of obs: 26, groups: floraison, 16
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.877e-01 5.000e-01 0.575 0.5650
## siteExt_Reserve 2.231e-01 6.708e-01 0.333 0.7394
## siteReserve 6.931e-01 6.124e-01 1.132 0.2577
## saisonFevrier 4.055e-01 6.455e-01 0.628 0.5299
## saisonJuin -2.877e-01 7.638e-01 -0.377 0.7064
## siteExt_Reserve:saisonFevrier 6.425e-10 9.037e-01 0.000 1.0000
## siteReserve:saisonFevrier -2.485e+00 1.242e+00 -2.001 0.0454 *
## siteExt_Reserve:saisonJuin -6.286e-01 1.133e+00 -0.555 0.5790
## siteReserve:saisonJuin 2.877e-01 9.129e-01 0.315 0.7527
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv ssnFvr sasnJn sE_R:F stRs:F sE_R:J
## sitExt_Rsrv -0.745
## siteReserve -0.816 0.609
## saisonFevrr -0.775 0.577 0.632
## saisonJuin -0.655 0.488 0.535 0.507
## stExt_Rsr:F 0.553 -0.742 -0.452 -0.714 -0.362
## stRsrv:ssnF 0.403 -0.300 -0.493 -0.520 -0.264 0.371
## stExt_Rsr:J 0.441 -0.592 -0.360 -0.342 -0.674 0.440 0.178
## stRsrv:ssnJ 0.548 -0.408 -0.671 -0.424 -0.837 0.303 0.331 0.564
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')
anova(glmco2)
## Analysis of Variance Table
## npar Sum Sq Mean Sq F value
## site 2 1.6518 0.82589 0.8259
## saison 2 0.7062 0.35308 0.3531
## site:saison 4 6.9067 1.72668 1.7267
r.squaredGLMM(glmco2)
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## boundary (singular) fit: see help('isSingular')
## R2m R2c
## delta 0.4319689 0.4319689
## lognormal 0.4941881 0.4941881
## trigamma 0.3570453 0.3570453
plot(simulateResiduals(glmco1))
plot(simulateResiduals(glmco2))
emco1 <- lsmeans(glmco1, ~ site, by="saison")
pairs(emco1)
## saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.511 0.516 Inf 0.989 0.5837
## (Bas-fond) - Reserve -0.470 0.403 Inf -1.166 0.4736
## Ext_Reserve - Reserve -0.981 0.479 Inf -2.049 0.1008
##
## saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 1.099 0.775 Inf 1.418 0.3314
## (Bas-fond) - Reserve 0.693 0.548 Inf 1.266 0.4148
## Ext_Reserve - Reserve -0.405 0.837 Inf -0.485 0.8786
##
## saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.118 0.486 Inf -0.242 0.9681
## (Bas-fond) - Reserve -0.811 0.425 Inf -1.908 0.1362
## Ext_Reserve - Reserve -0.693 0.408 Inf -1.698 0.2060
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emco2 <- lsmeans(glmco2, ~ site, by="saison")
pairs(emco2)
## saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.223 0.671 Inf -0.333 0.9408
## (Bas-fond) - Reserve -0.693 0.612 Inf -1.132 0.4944
## Ext_Reserve - Reserve -0.470 0.570 Inf -0.824 0.6878
##
## saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.223 0.606 Inf -0.369 0.9279
## (Bas-fond) - Reserve 1.792 1.080 Inf 1.659 0.2212
## Ext_Reserve - Reserve 2.015 1.095 Inf 1.839 0.1568
##
## saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.405 0.913 Inf 0.444 0.8970
## (Bas-fond) - Reserve -0.981 0.677 Inf -1.449 0.3159
## Ext_Reserve - Reserve -1.386 0.791 Inf -1.754 0.1855
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
Autres - Richesse et abondance Filet
glmau1<-glmer(rspe ~ site*saison+(1|floraison), data = syntfiletau, family = poisson, nAGQ=2)
## boundary (singular) fit: see help('isSingular')
glmau2<-glmer(rspe ~ site*saison+(1|floraison), data = syntpiegeau, family = poisson, nAGQ=2)
## boundary (singular) fit: see help('isSingular')
summary(glmau1)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * saison + (1 | floraison)
## Data: syntfiletau
##
## AIC BIC logLik deviance df.resid
## 65.0 82.6 -22.5 45.0 33
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.56144 -0.59628 -0.09759 0.32081 3.04256
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 0 0
## Number of obs: 43, groups: floraison, 17
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.43508 0.21822 6.576 4.82e-11 ***
## siteExt_Reserve -0.15415 0.32121 -0.480 0.6313
## siteReserve -0.47957 0.35291 -1.359 0.1742
## saisonFevrier -0.74194 0.38421 -1.931 0.0535 .
## saisonJuin -0.96508 0.41547 -2.323 0.0202 *
## siteExt_Reserve:saisonFevrier -0.02817 0.63496 -0.044 0.9646
## siteReserve:saisonFevrier 0.37421 0.57936 0.646 0.5183
## siteExt_Reserve:saisonJuin 0.90792 0.53572 1.695 0.0901 .
## siteReserve:saisonJuin 0.34604 0.62642 0.552 0.5807
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv ssnFvr sasnJn sE_R:F stRs:F sE_R:J
## sitExt_Rsrv -0.679
## siteReserve -0.618 0.420
## saisonFevrr -0.568 0.386 0.351
## saisonJuin -0.525 0.357 0.325 0.298
## stExt_Rsr:F 0.344 -0.506 -0.213 -0.605 -0.181
## stRsrv:ssnF 0.377 -0.256 -0.609 -0.663 -0.198 0.401
## stExt_Rsr:J 0.407 -0.600 -0.252 -0.231 -0.776 0.303 0.153
## stRsrv:ssnJ 0.348 -0.237 -0.563 -0.198 -0.663 0.120 0.343 0.514
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')
anova(glmau1)
## Analysis of Variance Table
## npar Sum Sq Mean Sq F value
## site 2 3.8618 1.9309 1.9309
## saison 2 7.2933 3.6467 3.6467
## site:saison 4 4.1098 1.0274 1.0274
r.squaredGLMM(glmau1)
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## R2m R2c
## delta 0.2694296 0.2694296
## lognormal 0.3050565 0.3050565
## trigamma 0.2309662 0.2309662
summary(glmau2)
## Generalized linear mixed model fit by maximum likelihood (Adaptive
## Gauss-Hermite Quadrature, nAGQ = 2) [glmerMod]
## Family: poisson ( log )
## Formula: rspe ~ site * saison + (1 | floraison)
## Data: syntpiegeau
##
## AIC BIC logLik deviance df.resid
## 35.9 48.4 -7.9 15.9 16
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.41421 -0.55629 0.06455 0.50000 1.41421
##
## Random effects:
## Groups Name Variance Std.Dev.
## floraison (Intercept) 0 0
## Number of obs: 26, groups: floraison, 16
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.386e+00 2.887e-01 4.802 1.57e-06 ***
## siteExt_Reserve 1.500e-13 4.082e-01 0.000 1.0000
## siteReserve -8.701e-02 4.174e-01 -0.208 0.8349
## saisonFevrier 5.108e-01 3.651e-01 1.399 0.1618
## saisonJuin -1.099e+00 5.774e-01 -1.903 0.0571 .
## siteExt_Reserve:saisonFevrier 1.823e-01 5.284e-01 0.345 0.7300
## siteReserve:saisonFevrier -5.108e-01 5.614e-01 -0.910 0.3629
## siteExt_Reserve:saisonJuin 8.109e-01 7.265e-01 1.116 0.2643
## siteReserve:saisonJuin 6.466e-01 7.531e-01 0.859 0.3905
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) stEx_R stRsrv ssnFvr sasnJn sE_R:F stRs:F sE_R:J
## sitExt_Rsrv -0.707
## siteReserve -0.692 0.489
## saisonFevrr -0.791 0.559 0.547
## saisonJuin -0.500 0.354 0.346 0.395
## stExt_Rsr:F 0.546 -0.773 -0.378 -0.691 -0.273
## stRsrv:ssnF 0.514 -0.364 -0.744 -0.650 -0.257 0.450
## stExt_Rsr:J 0.397 -0.562 -0.275 -0.314 -0.795 0.434 0.204
## stRsrv:ssnJ 0.383 -0.271 -0.554 -0.303 -0.767 0.209 0.412 0.609
## optimizer (Nelder_Mead) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')
anova(glmau2)
## Analysis of Variance Table
## npar Sum Sq Mean Sq F value
## site 2 3.2790 1.6395 1.6395
## saison 2 13.2554 6.6277 6.6277
## site:saison 4 3.4134 0.8533 0.8533
r.squaredGLMM(glmau2)
## Warning: the null model is correct only if all variables used by the original
## model remain unchanged.
## R2m R2c
## delta 0.4782091 0.4782091
## lognormal 0.5082390 0.5082390
## trigamma 0.4446735 0.4446735
plot(simulateResiduals(glmau1))
plot(simulateResiduals(glmau2))
emau1 <- lsmeans(glmau1, ~ site, by="saison")
pairs(emau1)
## saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.154 0.321 Inf 0.480 0.8808
## (Bas-fond) - Reserve 0.480 0.353 Inf 1.359 0.3627
## Ext_Reserve - Reserve 0.325 0.364 Inf 0.894 0.6440
##
## saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.182 0.548 Inf 0.333 0.9408
## (Bas-fond) - Reserve 0.105 0.459 Inf 0.229 0.9714
## Ext_Reserve - Reserve -0.077 0.558 Inf -0.138 0.9896
##
## saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.754 0.429 Inf -1.758 0.1839
## (Bas-fond) - Reserve 0.134 0.518 Inf 0.258 0.9640
## Ext_Reserve - Reserve 0.887 0.449 Inf 1.976 0.1182
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
emau2 <- lsmeans(glmau2, ~ site, by="saison")
pairs(emau2)
## saison = Aout:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve 0.000 0.408 Inf 0.000 1.0000
## (Bas-fond) - Reserve 0.087 0.417 Inf 0.208 0.9763
## Ext_Reserve - Reserve 0.087 0.417 Inf 0.208 0.9763
##
## saison = Fevrier:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.182 0.335 Inf -0.544 0.8498
## (Bas-fond) - Reserve 0.598 0.375 Inf 1.593 0.2488
## Ext_Reserve - Reserve 0.780 0.392 Inf 1.992 0.1142
##
## saison = Juin:
## contrast estimate SE df z.ratio p.value
## (Bas-fond) - Ext_Reserve -0.811 0.601 Inf -1.349 0.3678
## (Bas-fond) - Reserve -0.560 0.627 Inf -0.893 0.6448
## Ext_Reserve - Reserve 0.251 0.504 Inf 0.499 0.8719
##
## Results are given on the log (not the response) scale.
## P value adjustment: tukey method for comparing a family of 3 estimates
#Annexe : Permanova Saison selon les Ordres
#Supprimer les lignes vides
m_filet<-filet[,1:406]
m_fileth<-subset(m_filet,m_filet$ordre=="Hymenoptera")
m_fileth$nul<-apply(m_fileth[,6:406],1,sum)
m_fileth<-subset(m_fileth,m_fileth$nul !=0)
m_piege<-piege[,1:406]
m_piegeh<-subset(m_piege,m_piege$ordre=="Hymenoptera")
m_piegeh$nul<-apply(m_piegeh[,6:406],1,sum)
m_piegeh<-subset(m_piegeh,m_piegeh$nul !=0)
# Résultats
filet.divh<-adonis2(m_fileth[,6:406]~as.factor(m_fileth$Saison), data=m_fileth, permutations=5000)
filet.divh
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_fileth[, 6:406] ~ as.factor(m_fileth$Saison), data = m_fileth, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_fileth$Saison) 2 3.999 0.23264 6.0635 2e-04 ***
## Residual 40 13.190 0.76736
## Total 42 17.189 1.00000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
piege.divh<-adonis2(m_piegeh[,6:406]~as.factor(m_piegeh$Saison), data=m_piegeh, permutations=5000)
piege.divh
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_piegeh[, 6:406] ~ as.factor(m_piegeh$Saison), data = m_piegeh, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_piegeh$Saison) 2 1.9716 0.16878 2.3351 2e-04 ***
## Residual 23 9.7099 0.83122
## Total 25 11.6816 1.00000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Diptera
m_filetd<-subset(m_filet,m_filet$ordre=="Diptera")
m_filetd$nul<-apply(m_filetd[,6:406],1,sum)
m_filetd<-subset(m_filetd,m_filetd$nul !=0)
m_pieged<-subset(m_piege,m_piege$ordre=="Diptera")
m_pieged$nul<-apply(m_pieged[,6:406],1,sum)
m_pieged<-subset(m_pieged,m_pieged$nul !=0)
# Résultats
filet.divd<-adonis2(m_filetd[,6:406]~as.factor(m_filetd$Saison), data=m_filetd, permutations=5000)
filet.divd
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_filetd[, 6:406] ~ as.factor(m_filetd$Saison), data = m_filetd, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_filetd$Saison) 2 4.8161 0.28055 7.409 2e-04 ***
## Residual 38 12.3508 0.71945
## Total 40 17.1669 1.00000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
piege.divd<-adonis2(m_pieged[,6:406]~as.factor(m_pieged$Saison), data=m_pieged, permutations=5000)
piege.divd
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_pieged[, 6:406] ~ as.factor(m_pieged$Saison), data = m_pieged, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_pieged$Saison) 2 2.4271 0.2052 3.0982 2e-04 ***
## Residual 24 9.4006 0.7948
## Total 26 11.8277 1.0000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Coleoptera
m_filetc<-subset(m_filet,m_filet$ordre=="Coleoptera")
m_filetc$nul<-apply(m_filetc[,6:406],1,sum)
m_filetc<-subset(m_filetc,m_filetc$nul !=0)
m_piegec<-subset(m_piege,m_piege$ordre=="Coleoptera")
m_piegec$nul<-apply(m_piegec[,6:406],1,sum)
m_piegec<-subset(m_piegec,m_piegec$nul !=0)
# Résultats
filet.divc<-adonis2(m_filetc[,6:406]~as.factor(m_filetc$Saison), data=m_filetc, permutations=5000)
filet.divc
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_filetc[, 6:406] ~ as.factor(m_filetc$Saison), data = m_filetc, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_filetc$Saison) 2 2.6351 0.16294 3.4064 2e-04 ***
## Residual 35 13.5374 0.83706
## Total 37 16.1726 1.00000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
piege.divc<-adonis2(m_piegec[,6:406]~as.factor(m_piegec$Saison), data=m_piegec, permutations=5000)
piege.divc
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_piegec[, 6:406] ~ as.factor(m_piegec$Saison), data = m_piegec, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_piegec$Saison) 2 1.7423 0.19102 2.1252 0.0009998 ***
## Residual 18 7.3786 0.80898
## Total 20 9.1209 1.00000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Autres
m_fileta<-subset(m_filet,m_filet$ordre=="Autres")
m_fileta$nul<-apply(m_fileta[,6:406],1,sum)
m_fileta<-subset(m_fileta,m_fileta$nul !=0)
m_piegea<-subset(m_piege,m_piege$ordre=="Autres")
m_piegea$nul<-apply(m_piegea[,6:406],1,sum)
m_piegea<-subset(m_piegea,m_piegea$nul !=0)
# Résultats
filet.diva<-adonis2(m_fileta[,6:406]~as.factor(m_fileta$Saison), data=m_fileta, permutations=5000)
filet.diva
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_fileta[, 6:406] ~ as.factor(m_fileta$Saison), data = m_fileta, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_fileta$Saison) 2 2.7792 0.1641 3.5338 2e-04 ***
## Residual 36 14.1564 0.8359
## Total 38 16.9355 1.0000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
piege.diva<-adonis2(m_piegea[,6:406]~as.factor(m_piegea$Saison), data=m_piegea, permutations=5000)
piege.diva
## Permutation test for adonis under reduced model
## Terms added sequentially (first to last)
## Permutation: free
## Number of permutations: 5000
##
## adonis2(formula = m_piegea[, 6:406] ~ as.factor(m_piegea$Saison), data = m_piegea, permutations = 5000)
## Df SumOfSqs R2 F Pr(>F)
## as.factor(m_piegea$Saison) 2 3.4375 0.32891 5.8813 2e-04 ***
## Residual 24 7.0138 0.67109
## Total 26 10.4513 1.00000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Beta de Jaccard
library("entropart")
fipiaout<-subset(fipi, fipi$Saison=="Aout")
fipifev<-subset(fipi, fipi$Saison=="Fevrier")
fipijuin<-subset(fipi, fipi$Saison=="Juin")
sum(fipiaout[,6:406])
## [1] 985
sum(fipifev[,6:406])
## [1] 1134
sum(fipijuin[,6:406])
## [1] 1082
filetallaout<-subset(filetall, filetall$Saison=="Aout")
filetalljuin<-subset(filetall, filetall$Saison=="Juin")
filetallfev<-subset(filetall, filetall$Saison=="Fevrier")
sum(filetallaout[,6:406])
## [1] 401
sum(filetalljuin[,6:406])
## [1] 458
sum(filetallfev[,6:406])
## [1] 611
library(dplyr)
fipiaoutb<-summarise_each(fipiaout[,6:406],funs(sum))
## Warning: `summarise_each_()` was deprecated in dplyr 0.7.0.
## ℹ Please use `across()` instead.
## ℹ The deprecated feature was likely used in the dplyr package.
## Please report the issue at <https://github.com/tidyverse/dplyr/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## Warning: `funs()` was deprecated in dplyr 0.8.0.
## ℹ Please use a list of either functions or lambdas:
##
## # Simple named list: list(mean = mean, median = median)
##
## # Auto named with `tibble::lst()`: tibble::lst(mean, median)
##
## # Using lambdas list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
fipiaoutb<-t(fipiaoutb)
fipiaoutb<-data.frame(fipiaoutb)
fipiaoutb$presence<-fipiaoutb$fipiaoutb
fipiaoutb$presence<-as.numeric(fipiaoutb$presence)
#Dissimilarité Beta de Jaccard
library("dplyr")
library("ade4")
fipiaoutc<-summarise_each(fipiaout[,6:406], funs(sum))
## Warning: `funs()` was deprecated in dplyr 0.8.0.
## ℹ Please use a list of either functions or lambdas:
##
## # Simple named list: list(mean = mean, median = median)
##
## # Auto named with `tibble::lst()`: tibble::lst(mean, median)
##
## # Using lambdas list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
row.names(fipiaoutc)<-"Aout"
fipijuinc<-summarise_each(fipijuin[,6:406], funs(sum))
## Warning: `funs()` was deprecated in dplyr 0.8.0.
## ℹ Please use a list of either functions or lambdas:
##
## # Simple named list: list(mean = mean, median = median)
##
## # Auto named with `tibble::lst()`: tibble::lst(mean, median)
##
## # Using lambdas list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
row.names(fipijuinc)<-"Juin"
fipifevc<-summarise_each(fipifev[,6:406], funs(sum))
## Warning: `funs()` was deprecated in dplyr 0.8.0.
## ℹ Please use a list of either functions or lambdas:
##
## # Simple named list: list(mean = mean, median = median)
##
## # Auto named with `tibble::lst()`: tibble::lst(mean, median)
##
## # Using lambdas list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
row.names(fipifevc)<-"Fevrier"
fejuau<-bind_rows(fipifevc,fipiaoutc)
fejuau<-bind_rows(fejuau,fipijuinc)
DistJaccard <- dist.binary(fejuau, method = 1)
DistJaccard
## Fevrier Aout
## Aout 0.8891347
## Juin 0.9150794 0.9205043
Somme des espèces par saison
fipiaouta<-fipiaout[,6:406]
fipiaout2<-apply(fipiaouta,2,sum)
fipiaoutb<-bind_rows(fipiaouta,fipiaout2)
fipiaoutc<-t(fipiaoutb)
fipiaoutc<-data.frame(fipiaoutc)
fipiaoutc$somme<-fipiaoutc[,101]
fipiaoutd<-filter(fipiaoutc, fipiaoutc$somme > 0)
length(fipiaoutd$somme)
## [1] 188
fipifeva<-fipifev[,6:406]
fipifev2<-apply(fipifeva,2,sum)
fipifevb<-bind_rows(fipifeva,fipifev2)
fipifevc<-t(fipifevb)
fipifevc<-data.frame(fipifevc)
fipifevc$somme<-fipifevc[,85]
fipifevd<-filter(fipifevc, fipifevc$somme > 0)
length(fipifevd$somme)
## [1] 222
fipijuina<-fipijuin[,6:406]
fipijuin2<-apply(fipijuina,2,sum)
fipijuinb<-bind_rows(fipijuina,fipijuin2)
fipijuinc<-t(fipijuinb)
fipijuinc<-data.frame(fipijuinc)
fipijuinc$somme<-fipijuinc[,97]
fipijuind<-filter(fipijuinc, fipijuinc$somme > 0)
length(fipijuind$somme)
## [1] 114
#Relation floraison / diversité
ultrapoll<-bind_rows(syntppoll,syntfpoll)
ultrapoll$floraison<-as.numeric(ultrapoll$floraison)
glmflor<-lmer(rspe ~ floraison + (1|saison), data = ultrapoll) #Estimation des paramètres du modèle par la Quadrature de Gauss-Hermite (Bolker, 2008)
summary(glmflor)
## Linear mixed model fit by REML ['lmerMod']
## Formula: rspe ~ floraison + (1 | saison)
## Data: ultrapoll
##
## REML criterion at convergence: 324.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.7267 -0.5667 -0.1537 0.3168 4.1604
##
## Random effects:
## Groups Name Variance Std.Dev.
## saison (Intercept) 1.541 1.241
## Residual 5.880 2.425
## Number of obs: 69, groups: saison, 3
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 3.00700 0.90761 3.313
## floraison 0.07703 0.06260 1.231
##
## Correlation of Fixed Effects:
## (Intr)
## floraison -0.522
Anova(glmflor, type=2, method="chisq") #methode chis2 car glmer et type 3 car plan déséquilibré et présence d'une interaction
## Analysis of Deviance Table (Type II Wald chisquare tests)
##
## Response: rspe
## Chisq Df Pr(>Chisq)
## floraison 1.5143 1 0.2185
#Test des résidus
plot(glmflor)